Authors: Matthieu Dubois, Fran\c{c}ois Yvon, Pablo Piantanida
Abstract: The dissemination of Large Language Models (LLMs), trained at scale, and endowed with powerful text-generating abilities has vastly increased the threats posed by generative AI technologies by reducing the cost of producing harmful, toxic, faked or forged content. In response, various proposals have been made to automatically discriminate artificially generated from human-written texts, typically framing the problem as a classification problem. Most approaches evaluate an input document by a well-chosen detector LLM, assuming that low-perplexity scores reliably signal machine-made content. As using one single detector can induce brittleness of performance, we instead consider several and derive a new, theoretically grounded approach to combine their respective strengths. Our experiments, using a variety of generator LLMs, suggest that our method effectively increases the robustness of detection.
Authors: Qi Jia, Xiang Yue, Tianyu Zheng, Jie Huang, Bill Yuchen Lin
Abstract: We introduce SimulBench, a benchmark designed to evaluate large language models (LLMs) across a diverse collection of creative simulation scenarios, such as acting as a Linux terminal or playing text games with users. While these simulation tasks serve as effective measures of an LLM's general intelligence, they are seldom incorporated into existing benchmarks. A major challenge is to develop an evaluation framework for testing different LLMs fairly while preserving the multi-round interactive nature of simulation tasks between users and AI. To tackle this issue, we suggest using a fixed LLM as a user agent to engage with an LLM to collect dialogues first under different tasks. Then, challenging dialogue scripts are extracted for evaluating different target LLMs. To facilitate automatic assessment on \DataName{}, GPT-4 is employed as the evaluator, tasked with reviewing the quality of the final response generated by the target LLMs given multi-turn dialogue scripts. Our comprehensive experiments indicate that these simulation tasks continue to pose a significant challenge with their unique natures and show the gap between proprietary models and the most advanced open LLMs. For example, GPT-4-turbo outperforms LLaMA-3-70b-Chat on 18.55\% more cases.
Authors: Xia Hou, Qifeng Li, Tongliang Li
Abstract: Dialogue topic segmentation plays a crucial role in various types of dialogue modeling tasks. The state-of-the-art unsupervised DTS methods learn topic-aware discourse representations from conversation data through adjacent discourse matching and pseudo segmentation to further mine useful clues in unlabeled conversational relations. However, in multi-round dialogs, discourses often have co-references or omissions, leading to the fact that direct use of these discourses for representation learning may negatively affect the semantic similarity computation in the neighboring discourse matching task. In order to fully utilize the useful cues in conversational relations, this study proposes a novel unsupervised dialog topic segmentation method that combines the Utterance Rewriting (UR) technique with an unsupervised learning algorithm to efficiently utilize the useful cues in unlabeled dialogs by rewriting the dialogs in order to recover the co-referents and omitted words. Compared with existing unsupervised models, the proposed Discourse Rewriting Topic Segmentation Model (UR-DTS) significantly improves the accuracy of topic segmentation. The main finding is that the performance on DialSeg711 improves by about 6% in terms of absolute error score and WD, achieving 11.42% in terms of absolute error score and 12.97% in terms of WD. on Doc2Dial the absolute error score and WD improves by about 3% and 2%, respectively, resulting in SOTA reaching 35.17% in terms of absolute error score and 38.49% in terms of WD. This shows that the model is very effective in capturing the nuances of conversational topics, as well as the usefulness and challenges of utilizing unlabeled conversations.
Authors: Jonathan Li, Rohan Bhambhoria, Samuel Dahan, Xiaodan Zhu
Abstract: Generative AI models, such as the GPT and Llama series, have significant potential to assist laypeople in answering legal questions. However, little prior work focuses on the data sourcing, inference, and evaluation of these models in the context of laypersons. To this end, we propose a human-centric legal NLP pipeline, covering data sourcing, inference, and evaluation. We introduce and release a dataset, LegalQA, with real and specific legal questions spanning from employment law to criminal law, corresponding answers written by legal experts, and citations for each answer. We develop an automatic evaluation protocol for this dataset, then show that retrieval-augmented generation from only 850 citations in the train set can match or outperform internet-wide retrieval, despite containing 9 orders of magnitude less data. Finally, we propose future directions for open-sourced efforts, which fall behind closed-sourced models.
Authors: Hayato Tsukagoshi, Ryohei Sasano
Abstract: We report the development of Ruri, a series of Japanese general text embedding models. While the development of general-purpose text embedding models in English and multilingual contexts has been active in recent years, model development in Japanese remains insufficient. The primary reasons for this are the lack of datasets and the absence of necessary expertise. In this report, we provide a detailed account of the development process of Ruri. Specifically, we discuss the training of embedding models using synthesized datasets generated by LLMs, the construction of the reranker for dataset filtering and knowledge distillation, and the performance evaluation of the resulting general-purpose text embedding models.
Authors: Maike Behrendt, Stefan Sylvius Wagner, Stefan Harmeling
Abstract: Online spaces allow people to discuss important issues and make joint decisions, regardless of their location or time zone. However, without proper support and thoughtful design, these discussions often lack structure and politeness during the exchanges of opinions. Artificial intelligence (AI) represents an opportunity to support both participants and organizers of large-scale online participation processes. In this paper, we present an extension of adhocracy+, a large-scale open source participation platform, that provides two additional debate modules that are supported by AI to enhance the discussion quality and participant interaction.
Authors: Woojin Chung, Jiwoo Hong, Na Min An, James Thorne, Se-Young Yun
Abstract: Stable pre-training is essential for achieving better-performing language models. However, tracking pre-training stability by calculating gradient variance at every step is impractical due to the significant computational costs. We explore Token Embedding Variability (TEV) as a simple and efficient proxy for assessing pre-training stability in language models with pre-layer normalization, given that shallower layers are more prone to gradient explosion (section 2.2). Moreover, we propose Multi-head Low-Rank Attention (MLRA) as an architecture to alleviate such instability by limiting the exponential growth of output embedding variance, thereby preventing the gradient explosion (section 3.2). Empirical results on GPT-2 with MLRA demonstrate increased stability and lower perplexity, particularly in deeper models.
Authors: Zhiyuan Tang, Dong Wang, Shen Huang, Shidong Shang
Abstract: Large Language Models (LLMs) have demonstrated substantial potential for error correction in Automatic Speech Recognition (ASR). However, most research focuses on utterances from short-duration speech recordings, which are the predominant form of speech data for supervised ASR training. This paper investigates the effectiveness of LLMs for error correction in full-text generated by ASR systems from longer speech recordings, such as transcripts from podcasts, news broadcasts, and meetings. First, we develop a Chinese dataset for full-text error correction, named ChFT, utilizing a pipeline that involves text-to-speech synthesis, ASR, and error-correction pair extractor. This dataset enables us to correct errors across contexts, including both full-text and segment, and to address a broader range of error types, such as punctuation restoration and inverse text normalization, thus making the correction process comprehensive. Second, we fine-tune a pre-trained LLM on the constructed dataset using a diverse set of prompts and target formats, and evaluate its performance on full-text error correction. Specifically, we design prompts based on full-text and segment, considering various output formats, such as directly corrected text and JSON-based error-correction pairs. Through various test settings, including homogeneous, up-to-date, and hard test sets, we find that the fine-tuned LLMs perform well in the full-text setting with different prompts, each presenting its own strengths and weaknesses. This establishes a promising baseline for further research. The dataset is available on the website.
Authors: Tal Baumel (Ari), Andre Manoel (Ari), Daniel Jones (Ari), Shize Su (Ari), Huseyin Inan (Ari), Aaron (Ari), Bornstein, Robert Sim
Abstract: In the field of machine learning, domain-specific annotated data is an invaluable resource for training effective models. However, in the medical domain, this data often includes Personal Health Information (PHI), raising significant privacy concerns. The stringent regulations surrounding PHI limit the availability and sharing of medical datasets, which poses a substantial challenge for researchers and practitioners aiming to develop advanced machine learning models. In this paper, we introduce a novel method to "clone" datasets containing PHI. Our approach ensures that the cloned datasets retain the essential characteristics and utility of the original data without compromising patient privacy. By leveraging differential-privacy techniques and a novel fine-tuning task, our method produces datasets that are free from identifiable information while preserving the statistical properties necessary for model training. We conduct utility testing to evaluate the performance of machine learning models trained on the cloned datasets. The results demonstrate that our cloned datasets not only uphold privacy standards but also enhance model performance compared to those trained on traditional anonymized datasets. This work offers a viable solution for the ethical and effective utilization of sensitive medical data in machine learning, facilitating progress in medical research and the development of robust predictive models.
Authors: Zihang Peng, Daria Stepanova, Vinh Thinh Ho, Heike Adel, Alessandra Russo, Simon Ott
Abstract: Advances in information extraction have enabled the automatic construction of large knowledge graphs (e.g., Yago, Wikidata or Google KG), which are widely used in many applications like semantic search or data analytics. However, due to their semi-automatic construction, KGs are often incomplete. Rule learning methods, concerned with the extraction of frequent patterns from KGs and casting them into rules, can be applied to predict potentially missing facts. A crucial step in this process is rule ranking. Ranking of rules is especially challenging over highly incomplete or biased KGs (e.g., KGs predominantly storing facts about famous people), as in this case biased rules might fit the data best and be ranked at the top based on standard statistical metrics like rule confidence. To address this issue, prior works proposed to rank rules not only relying on the original KG but also facts predicted by a KG embedding model. At the same time, with the recent rise of Language Models (LMs), several works have claimed that LMs can be used as alternative means for KG completion. In this work, our goal is to verify to which extent the exploitation of LMs is helpful for improving the quality of rule learning systems.
Authors: Xiaoyun Jin, Mirjam Ernestus, R. Harald Baayen
Abstract: In Mandarin, the tonal contours of monosyllabic words produced in isolation or in careful speech are characterized by four lexical tones: a high-level tone (T1), a rising tone (T2), a dipping tone (T3) and a falling tone (T4). However, in spontaneous speech, the actual tonal realization of monosyllabic words can deviate significantly from these canonical tones due to intra-syllabic co-articulation and inter-syllabic co-articulation with adjacent tones. In addition, Chuang et al. (2024) recently reported that the tonal contours of disyllabic Mandarin words with T2-T4 tone pattern are co-determined by their meanings. Following up on their research, we present a corpus-based investigation of how the pitch contours of monosyllabic words are realized in spontaneous conversational Mandarin, focusing on the effects of contextual predictors on the one hand, and the way in words' meanings co-determine pitch contours on the other hand. We analyze the F0 contours of 3824 tokens of 63 different word types in a spontaneous Taiwan Mandarin corpus, using the generalized additive (mixed) model to decompose a given observed pitch contour into a set of component pitch contours. We show that the tonal context substantially modify a word's canonical tone. Once the effect of tonal context is controlled for, T2 and T3 emerge as low flat tones, contrasting with T1 as a high tone, and with T4 as a high-to-mid falling tone. The neutral tone (T0), which in standard descriptions, is realized based on the preceding tone, emerges as a low tone in its own right, modified by the other predictors in the same way as the standard tones T1, T2, T3, and T4. We also show that word, and even more so, word sense, co-determine words' F0 contours. Analyses of variable importance using random forests further supported the substantial effect of tonal context and an effect of word sense.
Authors: Huiyuan Xie, Felix Steffek, Joana Ribeiro de Faria, Christine Carter, Jonathan Rutherford
Abstract: This paper explores the intersection of technological innovation and access to justice by developing a benchmark for predicting case outcomes in the UK Employment Tribunal (UKET). To address the challenge of extensive manual annotation, the study employs a large language model (LLM) for automatic annotation, resulting in the creation of the CLC-UKET dataset. The dataset consists of approximately 19,000 UKET cases and their metadata. Comprehensive legal annotations cover facts, claims, precedent references, statutory references, case outcomes, reasons and jurisdiction codes. Facilitated by the CLC-UKET data, we examine a multi-class case outcome prediction task in the UKET. Human predictions are collected to establish a performance reference for model comparison. Empirical results from baseline models indicate that finetuned transformer models outperform zero-shot and few-shot LLMs on the UKET prediction task. The performance of zero-shot LLMs can be enhanced by integrating task-related information into few-shot examples. We hope that the CLC-UKET dataset, along with human annotations and empirical findings, can serve as a valuable benchmark for employment-related dispute resolution.
Authors: Michael Ong, Sean Robertson, Leo Peckham, Alba Jorquera Jimenez de Aberasturi, Paula Arkhangorodsky, Robin Huo, Aman Sakhardande, Mark Hallap, Naomi Nagy, Ewan Dunbar
Abstract: We introduce the Faetar Automatic Speech Recognition Benchmark, a benchmark corpus designed to push the limits of current approaches to low-resource speech recognition. Faetar, a Franco-Proven\c{c}al variety spoken primarily in Italy, has no standard orthography, has virtually no existing textual or speech resources other than what is included in the benchmark, and is quite different from other forms of Franco-Proven\c{c}al. The corpus comes from field recordings, most of which are noisy, for which only 5 hrs have matching transcriptions, and for which forced alignment is of variable quality. The corpus contains an additional 20 hrs of unlabelled speech. We report baseline results from state-of-the-art multilingual speech foundation models with a best phone error rate of 30.4%, using a pipeline that continues pre-training on the foundation model using the unlabelled set.
Authors: Gil Ayache, Menachem Pirchi, Aviv Navon, Aviv Shamsian, Gill Hetz, Joseph Keshet
Abstract: Integrating named entity recognition (NER) with automatic speech recognition (ASR) can significantly enhance transcription accuracy and informativeness. In this paper, we introduce WhisperNER, a novel model that allows joint speech transcription and entity recognition. WhisperNER supports open-type NER, enabling recognition of diverse and evolving entities at inference. Building on recent advancements in open NER research, we augment a large synthetic dataset with synthetic speech samples. This allows us to train WhisperNER on a large number of examples with diverse NER tags. During training, the model is prompted with NER labels and optimized to output the transcribed utterance along with the corresponding tagged entities. To evaluate WhisperNER, we generate synthetic speech for commonly used NER benchmarks and annotate existing ASR datasets with open NER tags. Our experiments demonstrate that WhisperNER outperforms natural baselines on both out-of-domain open type NER and supervised finetuning.
Authors: Zhengliang Liu, Yiwei Li, Oleksandra Zolotarevych, Rongwei Yang, Tianming Liu
Abstract: Large language models have demonstrated remarkable capabilities in natural language processing, yet their application to political discourse analysis remains underexplored. This paper introduces a novel approach to evaluating presidential debate performances using LLMs, addressing the longstanding challenge of objectively assessing debate outcomes. We propose a framework that analyzes candidates' "Policies, Persona, and Perspective" (3P) and how they resonate with the "Interests, Ideologies, and Identity" (3I) of four key audience groups: voters, businesses, donors, and politicians. Our method employs large language models to generate the LLM-POTUS Score, a quantitative measure of debate performance based on the alignment between 3P and 3I. We apply this framework to analyze transcripts from recent U.S. presidential debates, demonstrating its ability to provide nuanced, multi-dimensional assessments of candidate performances. Our results reveal insights into the effectiveness of different debating strategies and their impact on various audience segments. This study not only offers a new tool for political analysis but also explores the potential and limitations of using LLMs as impartial judges in complex social contexts. In addition, this framework provides individual citizens with an independent tool to evaluate presidential debate performances, which enhances democratic engagement and reduces reliance on potentially biased media interpretations and institutional influence, thereby strengthening the foundation of informed civic participation.
Authors: Andreas Opedal, Eleanor Chodroff, Ryan Cotterell, Ethan Gotlieb Wilcox
Abstract: We present a new perspective on how readers integrate context during real-time language comprehension. Our proposals build on surprisal theory, which posits that the processing effort of a linguistic unit (e.g., a word) is an affine function of its in-context information content. We first observe that surprisal is only one out of many potential ways that a contextual predictor can be derived from a language model. Another one is the pointwise mutual information (PMI) between a unit and its context, which turns out to yield the same predictive power as surprisal when controlling for unigram frequency. Moreover, both PMI and surprisal are correlated with frequency. This means that neither PMI nor surprisal contains information about context alone. In response to this, we propose a technique where we project surprisal onto the orthogonal complement of frequency, yielding a new contextual predictor that is uncorrelated with frequency. Our experiments show that the proportion of variance in reading times explained by context is a lot smaller when context is represented by the orthogonalized predictor. From an interpretability standpoint, this indicates that previous studies may have overstated the role that context has in predicting reading times.
Authors: Aaron Steiner, Ralph Peeters, Christian Bizer
Abstract: Generative large language models (LLMs) are a promising alternative to pre-trained language models for entity matching due to their high zero-shot performance and their ability to generalize to unseen entities. Existing research on using LLMs for entity matching has focused on prompt engineering and in-context learning. This paper explores the potential of fine-tuning LLMs for entity matching. We analyze fine-tuning along two dimensions: 1) The representation of training examples, where we experiment with adding different types of LLM-generated explanations to the training set, and 2) the selection and generation of training examples using LLMs. In addition to the matching performance on the source dataset, we investigate how fine-tuning affects the model's ability to generalize to other in-domain datasets as well as across topical domains. Our experiments show that fine-tuning significantly improves the performance of the smaller models while the results for the larger models are mixed. Fine-tuning also improves the generalization to in-domain datasets while hurting cross-domain transfer. We show that adding structured explanations to the training set has a positive impact on the performance of three out of four LLMs, while the proposed example selection and generation methods only improve the performance of Llama 3.1 8B while decreasing the performance of GPT-4o Mini.
Authors: Hyunjong Ok, Suho Yoo, Jaeho Lee
Abstract: Recent studies have identified that language models, pretrained on text-only datasets, often lack elementary visual knowledge, \textit{e.g.,} colors of everyday objects. Motivated by this observation, we ask whether a similar shortcoming exists in terms of the \textit{auditory} knowledge. To answer this question, we construct a new dataset called AuditoryBench, which consists of two novel tasks for evaluating auditory knowledge. Based on our analysis using the benchmark, we find that language models also suffer from a severe lack of auditory knowledge. To address this limitation, we propose AudioBERT, a novel method to augment the auditory knowledge of BERT through a retrieval-based approach. First, we detect auditory knowledge spans in prompts to query our retrieval model efficiently. Then, we inject audio knowledge into BERT and switch on low-rank adaptation for effective adaptation when audio knowledge is required. Our experiments demonstrate that AudioBERT is quite effective, achieving superior performance on the AuditoryBench. The dataset and code are available at \bulurl{https://github.com/HJ-Ok/AudioBERT}.
Authors: Alisia Lupidi, Carlos Gemmell, Nicola Cancedda, Jane Dwivedi-Yu, Jason Weston, Jakob Foerster, Roberta Raileanu, Maria Lomeli
Abstract: Large Language Models still struggle in challenging scenarios that leverage structured data, complex reasoning, or tool usage. In this paper, we propose Source2Synth: a new method that can be used for teaching LLMs new skills without relying on costly human annotations. Source2Synth takes as input a custom data source and produces synthetic data points with intermediate reasoning steps grounded in real-world sources. Source2Synth improves the dataset quality by discarding low-quality generations based on their answerability. We demonstrate the generality of this approach by applying it to two challenging domains: we test reasoning abilities in multi-hop question answering (MHQA), and tool usage in tabular question answering (TQA). Our method improves performance by 25.51% for TQA on WikiSQL and 22.57% for MHQA on HotPotQA compared to the fine-tuned baselines.
Authors: Jill Burstein, Geoffrey T. LaFlair, Kevin Yancey, Alina A. von Davier, Ravit Dotan
Abstract: Artificial intelligence (AI) creates opportunities for assessments, such as efficiencies for item generation and scoring of spoken and written responses. At the same time, it poses risks (such as bias in AI-generated item content). Responsible AI (RAI) practices aim to mitigate risks associated with AI. This chapter addresses the critical role of RAI practices in achieving test quality (appropriateness of test score inferences), and test equity (fairness to all test takers). To illustrate, the chapter presents a case study using the Duolingo English Test (DET), an AI-powered, high-stakes English language assessment. The chapter discusses the DET RAI standards, their development and their relationship to domain-agnostic RAI principles. Further, it provides examples of specific RAI practices, showing how these practices meaningfully address the ethical principles of validity and reliability, fairness, privacy and security, and transparency and accountability standards to ensure test equity and quality.
Authors: Ningyu Zhang, Zekun Xi, Yujie Luo, Peng Wang, Bozhong Tian, Yunzhi Yao, Jintian Zhang, Shumin Deng, Mengshu Sun, Lei Liang, Zhiqiang Zhang, Xiaowei Zhu, Jun Zhou, Huajun Chen
Abstract: Knowledge representation has been a central aim of AI since its inception. Symbolic Knowledge Graphs (KGs) and neural Large Language Models (LLMs) can both represent knowledge. KGs provide highly accurate and explicit knowledge representation, but face scalability issue; while LLMs offer expansive coverage of knowledge, but incur significant training costs and struggle with precise and reliable knowledge manipulation. To this end, we introduce OneEdit, a neural-symbolic prototype system for collaborative knowledge editing using natural language, which facilitates easy-to-use knowledge management with KG and LLM. OneEdit consists of three modules: 1) The Interpreter serves for user interaction with natural language; 2) The Controller manages editing requests from various users, leveraging the KG with rollbacks to handle knowledge conflicts and prevent toxic knowledge attacks; 3) The Editor utilizes the knowledge from the Controller to edit KG and LLM. We conduct experiments on two new datasets with KGs which demonstrate that OneEdit can achieve superior performance.
Authors: Shanu Vashishtha, Abhay Kumar, Lalitesh Morishetti, Kaushiki Nag, Kannan Achan
Abstract: E-commerce platforms have a vast catalog of items to cater to their customers' shopping interests. Most of these platforms assist their customers in the shopping process by offering optimized recommendation carousels, designed to help customers quickly locate their desired items. Many models have been proposed in academic literature to generate and enhance the ranking and recall set of items in these carousels. Conventionally, the accompanying carousel title text (header) of these carousels remains static. In most instances, a generic text such as "Items similar to your current viewing" is utilized. Fixed variations such as the inclusion of specific attributes "Other items from a similar seller" or "Items from a similar brand" in addition to "frequently bought together" or "considered together" are observed as well. This work proposes a novel approach to customize the header generation process of these carousels. Our work leverages user-generated reviews that lay focus on specific attributes (aspects) of an item that were favorably perceived by users during their interaction with the given item. We extract these aspects from reviews and train a graph neural network-based model under the framework of a conditional ranking task. We refer to our innovative methodology as Dynamic Text Snippets (DTS) which generates multiple header texts for an anchor item and its recall set. Our approach demonstrates the potential of utilizing user-generated reviews and presents a unique paradigm for exploring increasingly context-aware recommendation systems.
Authors: Gabriel de Souza P. Moreira, Ronay Ak, Benedikt Schifferer, Mengyao Xu, Radek Osmulski, Even Oldridge
Abstract: Ranking models play a crucial role in enhancing overall accuracy of text retrieval systems. These multi-stage systems typically utilize either dense embedding models or sparse lexical indices to retrieve relevant passages based on a given query, followed by ranking models that refine the ordering of the candidate passages by its relevance to the query. This paper benchmarks various publicly available ranking models and examines their impact on ranking accuracy. We focus on text retrieval for question-answering tasks, a common use case for Retrieval-Augmented Generation systems. Our evaluation benchmarks include models some of which are commercially viable for industrial applications. We introduce a state-of-the-art ranking model, NV-RerankQA-Mistral-4B-v3, which achieves a significant accuracy increase of ~14% compared to pipelines with other rerankers. We also provide an ablation study comparing the fine-tuning of ranking models with different sizes, losses and self-attention mechanisms. Finally, we discuss challenges of text retrieval pipelines with ranking models in real-world industry applications, in particular the trade-offs among model size, ranking accuracy and system requirements like indexing and serving latency / throughput.
Authors: Yanan Wang, Shuichiro Haruta, Donghuo Zeng, Julio Vizcarra, Mori Kurokawa
Abstract: Video question answering (VideoQA) is a task to predict the correct answer to questions posed about a given video. The system must comprehend spatial and temporal relationships among objects extracted from videos to perform causal and temporal reasoning. While prior works have focused on modeling individual object movements using transformer-based methods, they falter when capturing complex scenarios involving multiple objects (e.g., "a boy is throwing a ball in a hoop"). We propose a contrastive language event graph representation learning method called CLanG to address this limitation. Aiming to capture event representations associated with multiple objects, our method employs a multi-layer GNN-cluster module for adversarial graph representation learning, enabling contrastive learning between the question text and its relevant multi-object event graph. Our method outperforms a strong baseline, achieving up to 2.2% higher accuracy on two challenging VideoQA datasets, NExT-QA and TGIF-QA-R. In particular, it is 2.8% better than baselines in handling causal and temporal questions, highlighting its strength in reasoning multiple object-based events.
Authors: Yanan Wang, Shuichiro Haruta, Donghuo Zeng, Julio Vizcarra, Mori Kurokawa
Abstract: Capturing complex hierarchical human activities, from atomic actions (e.g., picking up one present, moving to the sofa, unwrapping the present) to contextual events (e.g., celebrating Christmas) is crucial for achieving high-performance video question answering (VideoQA). Recent works have expanded multimodal models (e.g., CLIP, LLaVA) to process continuous video sequences, enhancing the model's temporal reasoning capabilities. However, these approaches often fail to capture contextual events that can be decomposed into multiple atomic actions non-continuously distributed over relatively long-term sequences. In this paper, to leverage the spatial visual context representation capability of the CLIP model for obtaining non-continuous visual representations in terms of contextual events in videos, we convert long-term video sequences into a spatial image domain and finetune the multimodal model LLaVA for the VideoQA task. Our approach achieves competitive performance on the STAR task, in particular, with a 78.4% accuracy score, exceeding the current state-of-the-art score by 2.8 points on the NExTQA task.
Authors: Ekaterina Svikhnushina, Pearl Pu
Abstract: This paper explores the efficacy of online versus offline evaluation methods in assessing conversational chatbots, specifically comparing first-party direct interactions with third-party observational assessments. By extending a benchmarking dataset of user dialogs with empathetic chatbots with offline third-party evaluations, we present a systematic comparison between the feedback from online interactions and the more detached offline third-party evaluations. Our results reveal that offline human evaluations fail to capture the subtleties of human-chatbot interactions as effectively as online assessments. In comparison, automated third-party evaluations using a GPT-4 model offer a better approximation of first-party human judgments given detailed instructions. This study highlights the limitations of third-party evaluations in grasping the complexities of user experiences and advocates for the integration of direct interaction feedback in conversational AI evaluation to enhance system development and user satisfaction.
Authors: Xinying Lu, Jianli Xiao
Abstract: For traffic incident detection, the acquisition of data and labels is notably resource-intensive, rendering semi-supervised traffic incident detection both a formidable and consequential challenge. Thus, this paper focuses on traffic incident detection with a semi-supervised learning way. It proposes a semi-supervised learning model named FPMT within the framework of MixText. The data augmentation module introduces Generative Adversarial Networks to balance and expand the dataset. During the mix-up process in the hidden space, it employs a probabilistic pseudo-mixing mechanism to enhance regularization and elevate model precision. In terms of training strategy, it initiates with unsupervised training on all data, followed by supervised fine-tuning on a subset of labeled data, and ultimately completing the goal of semi-supervised training. Through empirical validation on four authentic datasets, our FPMT model exhibits outstanding performance across various metrics. Particularly noteworthy is its robust performance even in scenarios with low label rates.
Authors: Jake Street, Isibor Ihianle, Funminiyi Olajide, Ahmad Lotfi
Abstract: Online Grooming (OG) is a prevalent threat facing predominately children online, with groomers using deceptive methods to prey on the vulnerability of children on social media/messaging platforms. These attacks can have severe psychological and physical impacts, including a tendency towards revictimization. Current technical measures are inadequate, especially with the advent of end-to-end encryption which hampers message monitoring. Existing solutions focus on the signature analysis of child abuse media, which does not effectively address real-time OG detection. This paper proposes that OG attacks are complex, requiring the identification of specific communication patterns between adults and children. It introduces a novel approach leveraging advanced models such as BERT and RoBERTa for Message-Level Analysis and a Context Determination approach for classifying actor interactions, including the introduction of Actor Significance Thresholds and Message Significance Thresholds. The proposed method aims to enhance accuracy and robustness in detecting OG by considering the dynamic and multi-faceted nature of these attacks. Cross-dataset experiments evaluate the robustness and versatility of our approach. This paper's contributions include improved detection methodologies and the potential for application in various scenarios, addressing gaps in current literature and practices.
Authors: Aili Chen, Xuyang Ge, Ziquan Fu, Yanghua Xiao, Jiangjie Chen
Abstract: As global tourism expands and artificial intelligence technology advances, intelligent travel planning services have emerged as a significant research focus. Within dynamic real-world travel scenarios with multi-dimensional constraints, services that support users in automatically creating practical and customized travel itineraries must address three key objectives: Rationality, Comprehensiveness, and Personalization. However, existing systems with rule-based combinations or LLM-based planning methods struggle to fully satisfy these criteria. To overcome the challenges, we introduce TravelAgent, a travel planning system powered by large language models (LLMs) designed to provide reasonable, comprehensive, and personalized travel itineraries grounded in dynamic scenarios. TravelAgent comprises four modules: Tool-usage, Recommendation, Planning, and Memory Module. We evaluate TravelAgent's performance with human and simulated users, demonstrating its overall effectiveness in three criteria and confirming the accuracy of personalized recommendations.
Authors: Joy Hsu, Jiayuan Mao, Joshua B. Tenenbaum, Noah D. Goodman, Jiajun Wu
Abstract: A unique aspect of human visual understanding is the ability to flexibly interpret abstract concepts: acquiring lifted rules explaining what they symbolize, grounding them across familiar and unfamiliar contexts, and making predictions or reasoning about them. While off-the-shelf vision-language models excel at making literal interpretations of images (e.g., recognizing object categories such as tree branches), they still struggle to make sense of such visual abstractions (e.g., how an arrangement of tree branches may form the walls of a maze). To address this challenge, we introduce Deep Schema Grounding (DSG), a framework that leverages explicit structured representations of visual abstractions for grounding and reasoning. At the core of DSG are schemas--dependency graph descriptions of abstract concepts that decompose them into more primitive-level symbols. DSG uses large language models to extract schemas, then hierarchically grounds concrete to abstract components of the schema onto images with vision-language models. The grounded schema is used to augment visual abstraction understanding. We systematically evaluate DSG and different methods in reasoning on our new Visual Abstractions Dataset, which consists of diverse, real-world images of abstract concepts and corresponding question-answer pairs labeled by humans. We show that DSG significantly improves the abstract visual reasoning performance of vision-language models, and is a step toward human-aligned understanding of visual abstractions.
Authors: Hakan T. Otal, M. Abdullah Canbaz
Abstract: The rapid evolution of cyber threats necessitates innovative solutions for detecting and analyzing malicious activity. Honeypots, which are decoy systems designed to lure and interact with attackers, have emerged as a critical component in cybersecurity. In this paper, we present a novel approach to creating realistic and interactive honeypot systems using Large Language Models (LLMs). By fine-tuning a pre-trained open-source language model on a diverse dataset of attacker-generated commands and responses, we developed a honeypot capable of sophisticated engagement with attackers. Our methodology involved several key steps: data collection and processing, prompt engineering, model selection, and supervised fine-tuning to optimize the model's performance. Evaluation through similarity metrics and live deployment demonstrated that our approach effectively generates accurate and informative responses. The results highlight the potential of LLMs to revolutionize honeypot technology, providing cybersecurity professionals with a powerful tool to detect and analyze malicious activity, thereby enhancing overall security infrastructure.
Authors: Ashwini Gundappa, Emilia Ellsiepen, Lukas Schmitz, Frederik Wiehr, Vera Demberg
Abstract: The question of how cyber-physical systems should interact with human partners that can take over control or exert oversight is becoming more pressing, as these systems are deployed for an ever larger range of tasks. Drawing on the literatures on handing over control during semi-autonomous driving and human-robot interaction, we propose a design of a take-over request that combines an abstract pre-alert with an informative TOR: Relevant sensor information is highlighted on the controller's display, while a spoken message verbalizes the reason for the TOR. We conduct our study in the context of a semi-autonomous drone control scenario as our testbed. The goal of our online study is to assess in more detail what form a language-based TOR should take. Specifically, we compare a full sentence condition to shorter fragments, and test whether the visual highlighting should be done synchronously or asynchronously with the speech. Participants showed a higher accuracy in choosing the correct solution with our bi-modal TOR and felt that they were better able to recognize the critical situation. Using only fragments in the spoken message rather than full sentences did not lead to improved accuracy or faster reactions. Also, synchronizing the visual highlighting with the spoken message did not result in better accuracy and response times were even increased in this condition.
Authors: Sarah Schr\"oder, Alexander Schulz, Philip Kenneweg, Robert Feldhans, Fabian Hinder, Barbara Hammer
Abstract: Over the last years, word and sentence embeddings have established as text preprocessing for all kinds of NLP tasks and improved the performances significantly. Unfortunately, it has also been shown that these embeddings inherit various kinds of biases from the training data and thereby pass on biases present in society to NLP solutions. Many papers attempted to quantify bias in word or sentence embeddings to evaluate debiasing methods or compare different embedding models, usually with cosine-based metrics. However, lately some works have raised doubts about these metrics showing that even though such metrics report low biases, other tests still show biases. In fact, there is a great variety of bias metrics or tests proposed in the literature without any consensus on the optimal solutions. Yet we lack works that evaluate bias metrics on a theoretical level or elaborate the advantages and disadvantages of different bias metrics. In this work, we will explore different cosine based bias metrics. We formalize a bias definition based on the ideas from previous works and derive conditions for bias metrics. Furthermore, we thoroughly investigate the existing cosine-based metrics and their limitations to show why these metrics can fail to report biases in some cases. Finally, we propose a new metric, SAME, to address the shortcomings of existing metrics and mathematically prove that SAME behaves appropriately.
Authors: Sarah Schr\"oder, Alexander Schulz, Barbara Hammer
Abstract: With the enourmous popularity of large language models, many researchers have raised ethical concerns regarding social biases incorporated in such models. Several methods to measure social bias have been introduced, but apparently these methods do not necessarily agree regarding the presence or severity of bias. Furthermore, some works have shown theoretical issues or severe limitations with certain bias measures. For that reason, we introduce SAME, a novel bias score for semantic bias in embeddings. We conduct a thorough theoretical analysis as well as experiments to show its benefits compared to similar bias scores from the literature. We further highlight a substantial relation of semantic bias measured by SAME with downstream bias, a connection that has recently been argued to be negligible. Instead, we show that SAME is capable of measuring semantic bias and identify potential causes for social bias in downstream tasks.
Authors: Huahang Li, Longyu Feng, Shuangyin Li, Fei Hao, Chen Jason Zhang, Yuanfeng Song
Abstract: Entity resolution, the task of identifying and merging records that refer to the same real-world entity, is crucial in sectors like e-commerce, healthcare, and law enforcement. Large Language Models (LLMs) introduce an innovative approach to this task, capitalizing on their advanced linguistic capabilities and a ``pay-as-you-go'' model that provides significant advantages to those without extensive data science expertise. However, current LLMs are costly due to per-API request billing. Existing methods often either lack quality or become prohibitively expensive at scale. To address these problems, we propose an uncertainty reduction framework using LLMs to improve entity resolution results. We first initialize possible partitions of the entity cluster, refer to the same entity, and define the uncertainty of the result. Then, we reduce the uncertainty by selecting a few valuable matching questions for LLM verification. Upon receiving the answers, we update the probability distribution of the possible partitions. To further reduce costs, we design an efficient algorithm to judiciously select the most valuable matching pairs to query. Additionally, we create error-tolerant techniques to handle LLM mistakes and a dynamic adjustment method to reach truly correct partitions. Experimental results show that our method is efficient and effective, offering promising applications in real-world tasks.
Authors: Sarah Schr\"oder, Alexander Schulz, Fabian Hinder, Barbara Hammer
Abstract: Plenty of works have brought social biases in language models to attention and proposed methods to detect such biases. As a result, the literature contains a great deal of different bias tests and scores, each introduced with the premise to uncover yet more biases that other scores fail to detect. What severely lacks in the literature, however, are comparative studies that analyse such bias scores and help researchers to understand the benefits or limitations of the existing methods. In this work, we aim to close this gap for cosine based bias scores. By building on a geometric definition of bias, we propose requirements for bias scores to be considered meaningful for quantifying biases. Furthermore, we formally analyze cosine based scores from the literature with regard to these requirements. We underline these findings with experiments to show that the bias scores' limitations have an impact in the application case.
Authors: Siye Wu, Jian Xie, Jiangjie Chen, Tinghui Zhu, Kai Zhang, Yanghua Xiao
Abstract: By leveraging the retrieval of information from external knowledge databases, Large Language Models (LLMs) exhibit enhanced capabilities for accomplishing many knowledge-intensive tasks. However, due to the inherent flaws of current retrieval systems, there might exist irrelevant information within those retrieving top-ranked passages. In this work, we present a comprehensive investigation into the robustness of LLMs to different types of irrelevant information under various conditions. We initially introduce a framework to construct high-quality irrelevant information that ranges from semantically unrelated, partially related, and related to questions. Furthermore, our analysis demonstrates that the constructed irrelevant information not only scores highly on similarity metrics, being highly retrieved by existing systems, but also bears semantic connections to the context. Our investigation reveals that current LLMs still face challenges in discriminating highly semantically related information and can be easily distracted by these irrelevant yet misleading content. Besides, we also find that current solutions for handling irrelevant information have limitations in improving the robustness of LLMs to such distractions. All the resources are available on GitHub at https://github.com/Di-viner/LLM-Robustness-to-Irrelevant-Information.
URLs: https://github.com/Di-viner/LLM-Robustness-to-Irrelevant-Information.
Authors: Laurent Hasco\"et, Jean-Luc Bouchot, Shreyas Sunil Gaikwad, Sri Hari Krishna Narayanan, Jan H\"uckelheim
Abstract: Checkpointing is a cornerstone of data-flow reversal in adjoint algorithmic differentiation. Checkpointing is a storage/recomputation trade-off that can be applied at different levels, one of which being the call tree. We are looking for good placements of checkpoints onto the call tree of a given application, to reduce run time and memory footprint of its adjoint. There is no known optimal solution to this problem other than a combinatorial search on all placements. We propose a heuristics based on run-time profiling of the adjoint code. We describe implementation of this profiling tool in an existing source-transformation AD tool. We demonstrate the interest of this approach on test cases taken from the MITgcm ocean and atmospheric global circulation model. We discuss the limitations of our approach and propose directions to lift them.
Authors: Yotam Perlitz, Ariel Gera, Ofir Arviv, Asaf Yehudai, Elron Bandel, Eyal Shnarch, Michal Shmueli-Scheuer, Leshem Choshen
Abstract: Recent advancements in Language Models (LMs) have catalyzed the creation of multiple benchmarks, designed to assess these models' general capabilities. A crucial task, however, is assessing the validity of the benchmarks themselves. This is most commonly done via Benchmark Agreement Testing (BAT), where new benchmarks are validated against established ones using some agreement metric (e.g., rank correlation). Despite the crucial role of BAT for benchmark builders and consumers, there are no standardized procedures for such agreement testing. This deficiency can lead to invalid conclusions, fostering mistrust in benchmarks and upending the ability to properly choose the appropriate benchmark to use. By analyzing over 40 prominent benchmarks, we demonstrate how some overlooked methodological choices can significantly influence BAT results, potentially undermining the validity of conclusions. To address these inconsistencies, we propose a set of best practices for BAT and demonstrate how utilizing these methodologies greatly improves BAT robustness and validity. To foster adoption and facilitate future research,, we introduce BenchBench, a python package for BAT, and release the BenchBench-leaderboard, a meta-benchmark designed to evaluate benchmarks using their peers. Our findings underscore the necessity for standardized BAT, ensuring the robustness and validity of benchmark evaluations in the evolving landscape of language model research. BenchBench Package: github.com/IBM/BenchBench Leaderboard: hf.co/spaces/IBM/BenchBench
Authors: Zaiqiao Meng, Hao Zhou, Yifang Chen
Abstract: Visual Language Models (VLMs) are essential for various tasks, particularly visual reasoning tasks, due to their robust multi-modal information integration, visual reasoning capabilities, and contextual awareness. However, existing \VLMs{}' visual spatial reasoning capabilities are often inadequate, struggling even with basic tasks such as distinguishing left from right. To address this, we propose the \ours{} model, designed to enhance the visual spatial reasoning abilities of VLMS. ZeroVLM employs Zero-1-to-3, a 3D reconstruction model for obtaining different views of the input images and incorporates a prompting mechanism to further improve visual spatial reasoning. Experimental results on four visual spatial reasoning datasets show that our \ours{} achieves up to 19.48% accuracy improvement, which indicates the effectiveness of the 3D reconstruction and prompting mechanisms of our ZeroVLM.
Authors: Yikang Shen, Matthew Stallone, Mayank Mishra, Gaoyuan Zhang, Shawn Tan, Aditya Prasad, Adriana Meza Soria, David D. Cox, Rameswar Panda
Abstract: Finding the optimal learning rate for language model pretraining is a challenging task. This is not only because there is a complicated correlation between learning rate, batch size, number of training tokens, model size, and other hyperparameters but also because it is prohibitively expensive to perform a hyperparameter search for large language models with Billions or Trillions of parameters. Recent studies propose using small proxy models and small corpus to perform hyperparameter searches and transposing the optimal parameters to large models and large corpus. While the zero-shot transferability is theoretically and empirically proven for model size related hyperparameters, like depth and width, the zero-shot transfer from small corpus to large corpus is underexplored. In this paper, we study the correlation between optimal learning rate, batch size, and number of training tokens for the recently proposed WSD scheduler. After thousands of small experiments, we found a power-law relationship between variables and demonstrated its transferability across model sizes. Based on the observation, we propose a new learning rate scheduler, Power scheduler, that is agnostic about the number of training tokens and batch size. The experiment shows that combining the Power scheduler with Maximum Update Parameterization (muP) can consistently achieve impressive performance with one set of hyperparameters regardless of the number of training tokens, batch size, model size, and even model architecture. Our 3B dense and MoE models trained with the Power scheduler achieve comparable performance as state-of-the-art small language models. We open-source these pretrained models at https://ibm.biz/BdKhLa.
URLs: https://ibm.biz/BdKhLa.
Authors: Yijie Jin
Abstract: Multimodal Sentiment Analysis (MSA) leverages multiple data modals to analyze human sentiment. Existing MSA models generally employ cutting-edge multimodal fusion and representation learning-based methods to promote MSA capability. However, there are two key challenges: (i) in existing multimodal fusion methods, the decoupling of modal combinations and tremendous parameter redundancy, lead to insufficient fusion performance and efficiency; (ii) a challenging trade-off exists between representation capability and computational overhead in unimodal feature extractors and encoders. Our proposed GSIFN incorporates two main components to solve these problems: (i) a graph-structured and interlaced-masked multimodal Transformer. It adopts the Interlaced Mask mechanism to construct robust multimodal graph embedding, achieve all-modal-in-one Transformer-based fusion, and greatly reduce the computational overhead; (ii) a self-supervised learning framework with low computational overhead and high performance, which utilizes a parallelized LSTM with matrix memory to enhance non-verbal modal features for unimodal label generation. Evaluated on the MSA datasets CMU-MOSI, CMU-MOSEI, and CH-SIMS, GSIFN demonstrates superior performance with significantly lower computational overhead compared with previous state-of-the-art models.
Authors: Ramon Ferrer-i-Cancho
Abstract: We address the linguistic problem of the sequential arrangement of a head and its dependents from an information theoretic perspective. In particular, we consider the optimal placement of a head that maximizes the predictability of the sequence. We assume that dependents are statistically independent given a head, in line with the open-choice principle and the core assumptions of dependency grammar. We demonstrate the optimality of harmonic order, i.e., placing the head last maximizes the predictability of the head whereas placing the head first maximizes the predictability of dependents. We also show that postponing the head is the optimal strategy to maximize its predictability while bringing it forward is the optimal strategy to maximize the predictability of dependents. We unravel the advantages of the strategy of maximizing the predictability of the head over maximizing the predictability of dependents. Our findings shed light on the placements of the head adopted by real languages or emerging in different kinds of experiments.
Authors: Qin Dai, Benjamin Heinzerling, Kentaro Inui
Abstract: Entity tracking is essential for complex reasoning. To perform in-context entity tracking, language models (LMs) must bind an entity to its attribute (e.g., bind a container to its content) to recall attribute for a given entity. For example, given a context mentioning ``The coffee is in Box Z, the stone is in Box M, the map is in Box H'', to infer ``Box Z contains the coffee'' later, LMs must bind ``Box Z'' to ``coffee''. To explain the binding behaviour of LMs, Feng and Steinhardt (2023) introduce a Binding ID mechanism and state that LMs use a abstract concept called Binding ID (BI) to internally mark entity-attribute pairs. However, they have not directly captured the BI determinant information from entity activations. In this work, we provide a novel view of the Binding ID mechanism by localizing the prototype of BI information. Specifically, we discover that there exists a low-rank subspace in the hidden state (or activation) of LMs, that primarily encodes the order of entity and attribute and which is used as the prototype of BI to causally determine the binding. To identify this subspace, we choose principle component analysis as our first attempt and it is empirically proven to be effective. Moreover, we also discover that when editing representations along directions in the subspace, LMs tend to bind a given entity to other attributes accordingly. For example, by patching activations along the BI encoding direction we can make the LM to infer ``Box Z contains the stone'' and ``Box Z contains the map''.
Authors: Kyudan Jung, Nam-Joon Kim, Hyongon Ryu, Sieun Hyeon, Seung-jun Lee, Hyeok-jae Lee
Abstract: LaTeX is suitable for creating specially formatted documents in science, technology, mathematics, and computer science. Although the use of mathematical expressions in LaTeX format along with language models is increasing, there are no proper evaluation matrices to evaluate them. In this study, we propose TeXBLEU, a metric for evaluating mathematical expressions in the LaTeX format built on the n-gram-based BLEU metric widely used in translation tasks. The proposed TeXBLEU consists of a predefined tokenizer trained on the arXiv paper dataset and a fine-tuned embedding model with positional encoding. The TeXBLEU score was calculated by replacing BLUE's modified precision score with the similarity of n-gram-based tokens. TeXBLEU showed improvements of 86\%, 121\%, and 610\% over traditional evaluation metrics, such as BLEU, sacreBLEU, and Rouge, respectively, on the MathBridge dataset with 1,000 data points. The code is available at https://github.com/KyuDan1/TeXBLEU.
Authors: Lihu Chen, Ga\"el Varoquaux
Abstract: Large Language Models (LLMs) have made significant progress in advancing artificial general intelligence (AGI), leading to the development of increasingly large models such as GPT-4 and LLaMA-405B. However, scaling up model sizes results in exponentially higher computational costs and energy consumption, making these models impractical for academic researchers and businesses with limited resources. At the same time, Small Models (SMs) are frequently used in practical settings, although their significance is currently underestimated. This raises important questions about the role of small models in the era of LLMs, a topic that has received limited attention in prior research. In this work, we systematically examine the relationship between LLMs and SMs from two key perspectives: Collaboration and Competition. We hope this survey provides valuable insights for practitioners, fostering a deeper understanding of the contribution of small models and promoting more efficient use of computational resources. The code is available at https://github.com/tigerchen52/role_of_small_models
Authors: Shauli Ravfogel, Michael Twiton, Yoav Goldberg, Ryan Cotterell
Abstract: Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision. As these representations are increasingly being used in real-world applications, the inability to \emph{control} their content becomes an increasingly important problem. We formulate the problem of identifying and erasing a linear subspace that corresponds to a given concept, in order to prevent linear predictors from recovering the concept. We model this problem as a constrained, linear maximin game, and show that existing solutions are generally not optimal for this task. We derive a closed-form solution for certain objectives, and propose a convex relaxation, \method, that works well for others. When evaluated in the context of binary gender removal, the method recovers a low-dimensional subspace whose removal mitigates bias by intrinsic and extrinsic evaluation. We show that the method is highly expressive, effectively mitigating bias in deep nonlinear classifiers while maintaining tractability and interpretability.
Authors: Alejandro Lopez-Lira, Yuehua Tang
Abstract: We document the capability of large language models (LLMs) like ChatGPT to predict stock price movements using news headlines, even without direct financial training. ChatGPT scores significantly predict out-of-sample daily stock returns, subsuming traditional methods, and predictability is stronger among smaller stocks and following negative news. To explain these findings, we develop a theoretical model incorporating information capacity constraints, underreaction, limits-to-arbitrage, and LLMs. The model generates several key predictions, which we empirically test: (i) it establishes a critical threshold in AI capabilities necessary for profitable predictions, (ii) it demonstrates that only advanced LLMs can effectively interpret complex information, and (iii) it predicts that widespread LLM adoption can enhance market efficiency. Our results suggest that sophisticated return forecasting is an emerging capability of AI systems and that these technologies can alter information diffusion and decision-making processes in financial markets. Finally, we introduce an interpretability framework to evaluate LLMs' reasoning, contributing to AI transparency and economic decision-making.
Authors: Yu Zhang, Rongjie Huang, Ruiqi Li, JinZheng He, Yan Xia, Feiyang Chen, Xinyu Duan, Baoxing Huai, Zhou Zhao
Abstract: Style transfer for out-of-domain (OOD) singing voice synthesis (SVS) focuses on generating high-quality singing voices with unseen styles (such as timbre, emotion, pronunciation, and articulation skills) derived from reference singing voice samples. However, the endeavor to model the intricate nuances of singing voice styles is an arduous task, as singing voices possess a remarkable degree of expressiveness. Moreover, existing SVS methods encounter a decline in the quality of synthesized singing voices in OOD scenarios, as they rest upon the assumption that the target vocal attributes are discernible during the training phase. To overcome these challenges, we propose StyleSinger, the first singing voice synthesis model for zero-shot style transfer of out-of-domain reference singing voice samples. StyleSinger incorporates two critical approaches for enhanced effectiveness: 1) the Residual Style Adaptor (RSA) which employs a residual quantization module to capture diverse style characteristics in singing voices, and 2) the Uncertainty Modeling Layer Normalization (UMLN) to perturb the style attributes within the content representation during the training phase and thus improve the model generalization. Our extensive evaluations in zero-shot style transfer undeniably establish that StyleSinger outperforms baseline models in both audio quality and similarity to the reference singing voice samples. Access to singing voice samples can be found at https://stylesinger.github.io/.
Authors: Yuepeng Hu, Zhengyuan Jiang, Moyang Guo, Neil Gong
Abstract: Watermark has been widely deployed by industry to detect AI-generated images. The robustness of such watermark-based detector against evasion attacks in the white-box and black-box settings is well understood in the literature. However, the robustness in the no-box setting is much less understood. In this work, we propose a new transfer evasion attack to image watermark in the no-box setting. Our transfer attack adds a perturbation to a watermarked image to evade multiple surrogate watermarking models trained by the attacker itself, and the perturbed watermarked image also evades the target watermarking model. Our major contribution is to show that, both theoretically and empirically, watermark-based AI-generated image detector is not robust to evasion attacks even if the attacker does not have access to the watermarking model nor the detection API.
Authors: Shuai Zhao, Meihuizi Jia, Zhongliang Guo, Leilei Gan, Xiaoyu Xu, Xiaobao Wu, Jie Fu, Yichao Feng, Fengjun Pan, Luu Anh Tuan
Abstract: Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the demonstrable efficacy of LLMs, due to constraints on computational resources, users have to engage with open-source language models or outsource the entire training process to third-party platforms. However, research has demonstrated that language models are susceptible to potential security vulnerabilities, particularly in backdoor attacks. Backdoor attacks are designed to introduce targeted vulnerabilities into language models by poisoning training samples or model weights, allowing attackers to manipulate model responses through malicious triggers. While existing surveys on backdoor attacks provide a comprehensive overview, they lack an in-depth examination of backdoor attacks specifically targeting LLMs. To bridge this gap and grasp the latest trends in the field, this paper presents a novel perspective on backdoor attacks for LLMs by focusing on fine-tuning methods. Specifically, we systematically classify backdoor attacks into three categories: full-parameter fine-tuning, parameter-efficient fine-tuning, and no fine-tuning Based on insights from a substantial review, we also discuss crucial issues for future research on backdoor attacks, such as further exploring attack algorithms that do not require fine-tuning, or developing more covert attack algorithms.
Authors: Fanfan Liu, Feng Yan, Liming Zheng, Chengjian Feng, Yiyang Huang, Lin Ma
Abstract: Utilizing Vision-Language Models (VLMs) for robotic manipulation represents a novel paradigm, aiming to enhance the model's ability to generalize to new objects and instructions. However, due to variations in camera specifications and mounting positions, existing methods exhibit significant performance disparities across different robotic platforms. To address this challenge, we propose RoboUniView in this paper, an innovative approach that decouples visual feature extraction from action learning. We first learn a unified view representation from multi-perspective views by pre-training on readily accessible data, and then derive actions from this unified view representation to control robotic manipulation. This unified view representation more accurately mirrors the physical world and is not constrained by the robotic platform's camera parameters. Thanks to this methodology, we achieve state-of-the-art performance on the demanding CALVIN benchmark, enhancing the success rate in the $D \to D$ setting from 93.0% to 96.2%, and in the $ABC \to D$ setting from 92.2% to 94.2%. Moreover, our model exhibits outstanding adaptability and flexibility: it maintains high performance under unseen camera parameters, can utilize multiple datasets with varying camera parameters, and is capable of joint cross-task learning across datasets. Code is provided for re-implementation. https://github.com/liufanfanlff/RoboUniview
Authors: Yoshitaka Inoue, Tianci Song, Tianfan Fu
Abstract: Drug repurposing offers a promising avenue for accelerating drug development by identifying new therapeutic potentials of existing drugs. In this paper, we propose a multi-agent framework to enhance the drug repurposing process using state-of-the-art machine learning techniques and knowledge integration. Our framework comprises several specialized agents: an AI Agent trains robust drug-target interaction (DTI) models; a Knowledge Graph Agent utilizes the drug-gene interaction database (DGIdb), DrugBank, Comparative Toxicogenomics Database (CTD), and Search Tool for Interactions of Chemicals (STITCH) to systematically extract DTIs; and a Search Agent interacts with biomedical literature to annotate and verify computational predictions. By integrating outputs from these agents, our system effectively harnesses diverse data sources, including external databases, to propose viable repurposing candidates. Preliminary results demonstrate the potential of our approach in not only predicting drug-disease interactions but also in reducing the time and cost associated with traditional drug discovery methods. This paper highlights the scalability of multi-agent systems in biomedical research and their role in driving innovation in drug repurposing. Our approach not only outperforms existing methods in predicting drug repurposing potential but also provides interpretable results, paving the way for more efficient and cost-effective drug discovery processes.
Authors: Qian Niu, Junyu Liu, Ziqian Bi, Pohsun Feng, Benji Peng, Keyu Chen, Ming Li
Abstract: This comprehensive review explores the intersection of Large Language Models (LLMs) and cognitive science, examining similarities and differences between LLMs and human cognitive processes. We analyze methods for evaluating LLMs cognitive abilities and discuss their potential as cognitive models. The review covers applications of LLMs in various cognitive fields, highlighting insights gained for cognitive science research. We assess cognitive biases and limitations of LLMs, along with proposed methods for improving their performance. The integration of LLMs with cognitive architectures is examined, revealing promising avenues for enhancing artificial intelligence (AI) capabilities. Key challenges and future research directions are identified, emphasizing the need for continued refinement of LLMs to better align with human cognition. This review provides a balanced perspective on the current state and future potential of LLMs in advancing our understanding of both artificial and human intelligence.
Authors: Weiwei Gu, Suresh Kondepudi, Lixiao Huang, Nakul Gopalan
Abstract: Continual and interactive robot learning is a challenging problem as the robot is present with human users who expect the robot to learn novel skills to solve novel tasks perpetually with sample efficiency. In this work we present a framework for robots to query and learn visuo-motor robot skills and task relevant information via natural language dialog interactions with human users. Previous approaches either focus on improving the performance of instruction following agents, or passively learn novel skills or concepts. Instead, we used dialog combined with a language-skill grounding embedding to query or confirm skills and/or tasks requested by a user. To achieve this goal, we developed and integrated three different components for our agent. Firstly, we propose a novel visual-motor control policy ACT with Low Rank Adaptation (ACT-LoRA), which enables the existing SoTA ACT model to perform few-shot continual learning. Secondly, we develop an alignment model that projects demonstrations across skill embodiments into a shared embedding allowing us to know when to ask questions and/or demonstrations from users. Finally, we integrated an existing LLM to interact with a human user to perform grounded interactive continual skill learning to solve a task. Our ACT-LoRA model learns novel fine-tuned skills with a 100% accuracy when trained with only five demonstrations for a novel skill while still maintaining a 74.75% accuracy on pre-trained skills in the RLBench dataset where other models fall significantly short. We also performed a human-subjects study with 8 subjects to demonstrate the continual learning capabilities of our combined framework. We achieve a success rate of 75% in the task of sandwich making with the real robot learning from participant data demonstrating that robots can learn novel skills or task knowledge from dialogue with non-expert users using our approach.