Authors: Sanad Aburass, Osama Dorgham, Jamil Al Shaqsi
This study presents an ensemble model combining LSTM, BiLSTM, CNN, GRU, and GloVe to classify gene mutations using Kaggle's Personalized Medicine: Redefining Cancer Treatment dataset. The results were compared against well-known transformers like as BERT, Electra, Roberta, XLNet, Distilbert, and their LSTM ensembles. Our model outperformed all other models in terms of accuracy, precision, recall, F1 score, and Mean Squared Error. Surprisingly, it also needed less training time, resulting in a perfect combination of performance and efficiency. This study demonstrates the utility of ensemble models for difficult tasks such as gene mutation classification.
Authors: Hadi Abdine, Michail Chatzianastasis, Costas Bouyioukos, Michalis Vazirgiannis
The complex nature of big biological systems pushed some scientists to classify its understanding under the inconceivable missions. Different leveled challenges complicated this task, one of is the prediction of a protein's function. In recent years, significant progress has been made in this field through the development of various machine learning approaches. However, most existing methods formulate the task as a multi-classification problem, i.e assigning predefined labels to proteins. In this work, we propose a novel approach, \textbf{Prot2Text}, which predicts a protein function's in a free text style, moving beyond the conventional binary or categorical classifications. By combining Graph Neural Networks(GNNs) and Large Language Models(LLMs), in an encoder-decoder framework, our model effectively integrates diverse data types including proteins' sequences, structures, and textual annotations. This multimodal approach allows for a holistic representation of proteins' functions, enabling the generation of detailed and accurate descriptions. To evaluate our model, we extracted a multimodal protein dataset from SwissProt, and demonstrate empirically the effectiveness of Prot2Text. These results highlight the transformative impact of multimodal models, specifically the fusion of GNNs and LLMs, empowering researchers with powerful tools for more accurate prediction of proteins' functions. The code, the models and a demo will be publicly released.
Authors: Liane Makatura, Michael Foshey, Bohan Wang, Felix HähnLein, Pingchuan Ma, Bolei Deng, Megan Tjandrasuwita, Andrew Spielberg, Crystal Elaine Owens, Peter Yichen Chen, Allan Zhao, Amy Zhu, Wil J Norton, Edward Gu, Joshua Jacob, Yifei Li, Adriana Schulz, Wojciech Matusik
The advancement of Large Language Models (LLMs), including GPT-4, provides exciting new opportunities for generative design. We investigate the application of this tool across the entire design and manufacturing workflow. Specifically, we scrutinize the utility of LLMs in tasks such as: converting a text-based prompt into a design specification, transforming a design into manufacturing instructions, producing a design space and design variations, computing the performance of a design, and searching for designs predicated on performance. Through a series of examples, we highlight both the benefits and the limitations of the current LLMs. By exposing these limitations, we aspire to catalyze the continued improvement and progression of these models.
Authors: Xuhai Xu, Bingshen Yao, Yuanzhe Dong, Hong Yu, James Hendler, Anind K. Dey, Dakuo Wang
The recent technology boost of large language models (LLMs) has empowered a variety of applications. However, there is very little research on understanding and improving LLMs' capability for the mental health domain. In this work, we present the first comprehensive evaluation of multiple LLMs, including Alpaca, Alpaca-LoRA, and GPT-3.5, on various mental health prediction tasks via online text data. We conduct a wide range of experiments, covering zero-shot prompting, few-shot prompting, and instruction finetuning. The results indicate the promising yet limited performance of LLMs with zero-shot and few-shot prompt designs for mental health tasks. More importantly, our experiments show that instruction finetuning can significantly boost the performance of LLMs for all tasks simultaneously. Our best-finetuned model, Mental-Alpaca, outperforms GPT-3.5 (25 times bigger) by 16.7\% on balanced accuracy and performs on par with the state-of-the-art task-specific model. We summarize our findings into a set of action guidelines for future researchers, engineers, and practitioners on how to empower LLMs with better mental health domain knowledge and become an expert in mental health prediction tasks.
Authors: Soowon Kim, Young-Eun Lee, Seo-Hyun Lee, Seong-Whan Lee
Decoding EEG signals for imagined speech is a challenging task due to the high-dimensional nature of the data and low signal-to-noise ratio. In recent years, denoising diffusion probabilistic models (DDPMs) have emerged as promising approaches for representation learning in various domains. Our study proposes a novel method for decoding EEG signals for imagined speech using DDPMs and a conditional autoencoder named Diff-E. Results indicate that Diff-E significantly improves the accuracy of decoding EEG signals for imagined speech compared to traditional machine learning techniques and baseline models. Our findings suggest that DDPMs can be an effective tool for EEG signal decoding, with potential implications for the development of brain-computer interfaces that enable communication through imagined speech.
Authors: Mayee F. Chen, Nicholas Roberts, Kush Bhatia, Jue Wang, Ce Zhang, Frederic Sala, Christopher Ré
The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new framework based on a simple hypothesis: just as humans acquire interdependent skills in a deliberate order, language models also follow a natural order when learning a set of skills from their training data. If such an order exists, it can be utilized for improved understanding of LMs and for data-efficient training. Using this intuition, our framework formalizes the notion of a skill and of an ordered set of skills in terms of the associated data. First, using both synthetic and real data, we demonstrate that these ordered skill sets exist, and that their existence enables more advanced skills to be learned with less data when we train on their prerequisite skills. Second, using our proposed framework, we introduce an online data sampling algorithm, Skill-It, over mixtures of skills for both continual pre-training and fine-tuning regimes, where the objective is to efficiently learn multiple skills in the former and an individual skill in the latter. On the LEGO synthetic in the continual pre-training setting, Skill-It obtains 36.5 points higher accuracy than random sampling. On the Natural Instructions dataset in the fine-tuning setting, Skill-It reduces the validation loss on the target skill by 13.6% versus training on data associated with the target skill itself. We apply our skills framework on the recent RedPajama dataset to continually pre-train a 3B-parameter LM, achieving higher accuracy on the LM Evaluation Harness with 1B tokens than the baseline approach of sampling uniformly over data sources with 3B tokens.
Authors: Angela Ramirez, Karik Agarwal, Juraj Juraska, Utkarsh Garg, Marilyn A. Walker
Dialogue systems need to produce responses that realize multiple types of dialogue acts (DAs) with high semantic fidelity. In the past, natural language generators (NLGs) for dialogue were trained on large parallel corpora that map from a domain-specific DA and its semantic attributes to an output utterance. Recent work shows that pretrained language models (LLMs) offer new possibilities for controllable NLG using prompt-based learning. Here we develop a novel few-shot overgenerate-and-rank approach that achieves the controlled generation of DAs. We compare eight few-shot prompt styles that include a novel method of generating from textual pseudo-references using a textual style transfer approach. We develop six automatic ranking functions that identify outputs with both the correct DA and high semantic accuracy at generation time. We test our approach on three domains and four LLMs. To our knowledge, this is the first work on NLG for dialogue that automatically ranks outputs using both DA and attribute accuracy. For completeness, we compare our results to fine-tuned few-shot models trained with 5 to 100 instances per DA. Our results show that several prompt settings achieve perfect DA accuracy, and near perfect semantic accuracy (99.81%) and perform better than few-shot fine-tuning.
Authors: Nimrod Dvir, Elaine Friedman, Suraj Commuri, Fan yang, Jennifer Romano
This study introduces and empirically tests a novel predictive model for digital information engagement (IE) - the READ model, an acronym for the four pivotal attributes of engaging information: Representativeness, Ease-of-use, Affect, and Distribution. Conceptualized within the theoretical framework of Cumulative Prospect Theory, the model integrates key cognitive biases with computational linguistics and natural language processing to develop a multidimensional perspective on information engagement. A rigorous testing protocol was implemented, involving 50 randomly selected pairs of synonymous words (100 words in total) from the WordNet database. These words' engagement levels were evaluated through a large-scale online survey (n = 80,500) to derive empirical IE metrics. The READ attributes for each word were then computed and their predictive efficacy examined. The findings affirm the READ model's robustness, accurately predicting a word's IE level and distinguishing the more engaging word from a pair of synonyms with an 84% accuracy rate. The READ model's potential extends across various domains, including business, education, government, and healthcare, where it could enhance content engagement and inform AI language model development and generative text work. Future research should address the model's scalability and adaptability across different domains and languages, thereby broadening its applicability and efficacy.
Authors: Nimrod Dvir, Elaine Friedman, Suraj Commuri, Fan Yang, Jennifer Romano
This research draws upon cognitive psychology and information systems studies to anticipate user engagement and decision-making on digital platforms. By employing natural language processing (NLP) techniques and insights from cognitive bias research, we delve into user interactions with synonyms within digital content. Our methodology synthesizes four cognitive biasesRepresentativeness, Ease-of-use, Affect, and Distributioninto the READ model. Through a comprehensive user survey, we assess the model's ability to predict user engagement, discovering that synonyms that accurately represent core ideas, are easy to understand, elicit emotional responses, and are commonly encountered, promote greater user engagement. Crucially, our work offers a fresh lens on human-computer interaction, digital behaviors, and decision-making processes. Our results highlight the promise of cognitive biases as potent indicators of user engagement, underscoring their significance in designing effective digital content across fields like education and marketing.
Authors: Renee D. White (1), Tristan Peng (1), Pann Sripitak (1), Alexander Rosenberg Johansen (1), Michael Snyder (1) (1) Stanford University
A clinical trial is a study that evaluates new biomedical interventions. To design new trials, researchers draw inspiration from those current and completed. In 2022, there were on average more than 100 clinical trials submitted to ClinicalTrials.gov every day, with each trial having a mean of approximately 1500 words [1]. This makes it nearly impossible to keep up to date. To mitigate this issue, we have created a batch clinical trial summarizer called CliniDigest using GPT-3.5. CliniDigest is, to our knowledge, the first tool able to provide real-time, truthful, and comprehensive summaries of clinical trials. CliniDigest can reduce up to 85 clinical trial descriptions (approximately 10,500 words) into a concise 200-word summary with references and limited hallucinations. We have tested CliniDigest on its ability to summarize 457 trials divided across 27 medical subdomains. For each field, CliniDigest generates summaries of $\mu=153,\ \sigma=69 $ words, each of which utilizes $\mu=54\%,\ \sigma=30\% $ of the sources. A more comprehensive evaluation is planned and outlined in this paper.
Authors: Erfan Shayegani, Yue Dong, Nael Abu-Ghazaleh
The rapid growth and increasing popularity of incorporating additional modalities (e.g., vision) into large language models (LLMs) has raised significant security concerns. This expansion of modality, akin to adding more doors to a house, unintentionally creates multiple access points for adversarial attacks. In this paper, by introducing adversarial embedding space attacks, we emphasize the vulnerabilities present in multi-modal systems that originate from incorporating off-the-shelf components like public pre-trained encoders in a plug-and-play manner into these systems. In contrast to existing work, our approach does not require access to the multi-modal system's weights or parameters but instead relies on the huge under-explored embedding space of such pre-trained encoders. Our proposed embedding space attacks involve seeking input images that reside within the dangerous or targeted regions of the extensive embedding space of these pre-trained components. These crafted adversarial images pose two major threats: 'Context Contamination' and 'Hidden Prompt Injection'-both of which can compromise multi-modal models like LLaVA and fully change the behavior of the associated language model. Our findings emphasize the need for a comprehensive examination of the underlying components, particularly pre-trained encoders, before incorporating them into systems in a plug-and-play manner to ensure robust security.
This paper presents a novel approach to assist students with dyslexia, ADHD, and short attention span in digesting any text-based information more efficiently. The proposed solution utilizes the Multilayer Perceptron (MLP) algorithm for complex text processing and summarization tasks. The tool leverages the T5 (Text-to-Text Transfer Transformer) model from Hugging Face, which treats every NLP task as a text generation task. The model is fine-tuned on specific tasks using a smaller dataset. The NLTK's Punkt Sentence Tokenizer is used to divide a text into a list of sentences. The application is served using Flask, a lightweight web server and framework. The tool also applies principles from Bionic Reading to enhance readability, which includes a bolding function and adjustments to line, word, and character spacing. The paper discusses the methodology, implementation, and results of the AI-based speed reading tool.
Authors: Subha Vadlamannati, Gözde Gül Şahin
In-context learning (ICL) for large language models has proven to be a powerful approach for many natural language processing tasks. However, determining the best method to select examples for ICL is nontrivial as the results can vary greatly depending on the quality, quantity, and order of examples used. In this paper, we conduct a case study on text simplification (TS) to investigate how to select the best and most robust examples for ICL. We propose Metric-Based in-context Learning (MBL) method that utilizes commonly used TS metrics such as SARI, compression ratio, and BERT-Precision for selection. Through an extensive set of experiments with various-sized GPT models on standard TS benchmarks such as TurkCorpus and ASSET, we show that examples selected by the top SARI scores perform the best on larger models such as GPT-175B, while the compression ratio generally performs better on smaller models such as GPT-13B and GPT-6.7B. Furthermore, we demonstrate that MBL is generally robust to example orderings and out-of-domain test sets, and outperforms strong baselines and state-of-the-art finetuned language models. Finally, we show that the behaviour of large GPT models can be implicitly controlled by the chosen metric. Our research provides a new framework for selecting examples in ICL, and demonstrates its effectiveness in text simplification tasks, breaking new ground for more accurate and efficient NLG systems.
Authors: Mohammad Majd Saad Al Deen, Maren Pielka, Jörn Hees, Bouthaina Soulef Abdou, Rafet Sifa
This paper addresses the classification of Arabic text data in the field of Natural Language Processing (NLP), with a particular focus on Natural Language Inference (NLI) and Contradiction Detection (CD). Arabic is considered a resource-poor language, meaning that there are few data sets available, which leads to limited availability of NLP methods. To overcome this limitation, we create a dedicated data set from publicly available resources. Subsequently, transformer-based machine learning models are being trained and evaluated. We find that a language-specific model (AraBERT) performs competitively with state-of-the-art multilingual approaches, when we apply linguistically informed pre-training methods such as Named Entity Recognition (NER). To our knowledge, this is the first large-scale evaluation for this task in Arabic, as well as the first application of multi-task pre-training in this context.
Authors: Shuzhou Yuan, Michael Färber
Large language models (LLMs) have been widely employed for graph-to-text generation tasks. However, the process of finetuning LLMs requires significant training resources and annotation work. In this paper, we explore the capability of generative models to generate descriptive text from graph data in a zero-shot setting. Specifically, we evaluate GPT-3 and ChatGPT on two graph-to-text datasets and compare their performance with that of finetuned LLM models such as T5 and BART. Our results demonstrate that generative models are capable of generating fluent and coherent text, achieving BLEU scores of 10.57 and 11.08 for the AGENDA and WebNLG datasets, respectively. However, our error analysis reveals that generative models still struggle with understanding the semantic relations between entities, and they also tend to generate text with hallucinations or irrelevant information. As a part of error analysis, we utilize BERT to detect machine-generated text and achieve high macro-F1 scores. We have made the text generated by generative models publicly available.
Authors: Dominik Macháček, Raj Dabre, Ondřej Bojar
Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription. In this paper, we build on top of Whisper and create Whisper-Streaming, an implementation of real-time speech transcription and translation of Whisper-like models. Whisper-Streaming uses local agreement policy with self-adaptive latency to enable streaming transcription. We show that Whisper-Streaming achieves high quality and 3.3 seconds latency on unsegmented long-form speech transcription test set, and we demonstrate its robustness and practical usability as a component in live transcription service at a multilingual conference.
Authors: Serkan Sulun, Pedro Oliveira, Paula Viana
We present a new large-scale emotion-labeled symbolic music dataset consisting of 12k MIDI songs. To create this dataset, we first trained emotion classification models on the GoEmotions dataset, achieving state-of-the-art results with a model half the size of the baseline. We then applied these models to lyrics from two large-scale MIDI datasets. Our dataset covers a wide range of fine-grained emotions, providing a valuable resource to explore the connection between music and emotions and, especially, to develop models that can generate music based on specific emotions. Our code for inference, trained models, and datasets are available online.
Authors: Pavel Přibáň, Ondřej Pražák
This paper presents a series of approaches aimed at enhancing the performance of Aspect-Based Sentiment Analysis (ABSA) by utilizing extracted semantic information from a Semantic Role Labeling (SRL) model. We propose a novel end-to-end Semantic Role Labeling model that effectively captures most of the structured semantic information within the Transformer hidden state. We believe that this end-to-end model is well-suited for our newly proposed models that incorporate semantic information. We evaluate the proposed models in two languages, English and Czech, employing ELECTRA-small models. Our combined models improve ABSA performance in both languages. Moreover, we achieved new state-of-the-art results on the Czech ABSA.
Authors: Fahime Same, Guanyi Chen, Kees van Deemter
In recent years, many NLP studies have focused solely on performance improvement. In this work, we focus on the linguistic and scientific aspects of NLP. We use the task of generating referring expressions in context (REG-in-context) as a case study and start our analysis from GREC, a comprehensive set of shared tasks in English that addressed this topic over a decade ago. We ask what the performance of models would be if we assessed them (1) on more realistic datasets, and (2) using more advanced methods. We test the models using different evaluation metrics and feature selection experiments. We conclude that GREC can no longer be regarded as offering a reliable assessment of models' ability to mimic human reference production, because the results are highly impacted by the choice of corpus and evaluation metrics. Our results also suggest that pre-trained language models are less dependent on the choice of corpus than classic Machine Learning models, and therefore make more robust class predictions.
Authors: Anna Moskvina, Bhushan Kotnis, Chris Catacata, Michael Janz, Nasrin Saef
Paraphrasing is the task of expressing an essential idea or meaning in different words. But how different should the words be in order to be considered an acceptable paraphrase? And can we exclusively use automated metrics to evaluate the quality of a paraphrase? We attempt to answer these questions by conducting experiments on a German data set and performing automatic and expert linguistic evaluation.
Authors: Ahmet Yavuz Uluslu, Gerold Schneider
In this paper, we present the first application of Native Language Identification (NLI) for the Turkish language. NLI involves predicting the writer's first language by analysing their writing in different languages. While most NLI research has focused on English, our study extends its scope to Turkish. We used the recently constructed Turkish Learner Corpus and employed a combination of three syntactic features (CFG production rules, part-of-speech n-grams and function words) with L2 texts to demonstrate their effectiveness in this task.
Authors: Shitou Zhang, Jingrui Hou, Siyuan Peng, Zuchao Li, Qibiao Hu, Ping Wang
Archives play a crucial role in preserving information and knowledge, and the exponential growth of such data necessitates efficient and automated tools for managing and utilizing archive information resources. Archival applications involve managing massive data that are challenging to process and analyze. Although LLMs have made remarkable progress in diverse domains, there are no publicly available archives tailored LLM. Addressing this gap, we introduce ArcGPT, to our knowledge, the first general-purpose LLM tailored to the archival field. To enhance model performance on real-world archival tasks, ArcGPT has been pre-trained on massive and extensive archival domain data. Alongside ArcGPT, we release AMBLE, a benchmark comprising four real-world archival tasks. Evaluation on AMBLE shows that ArcGPT outperforms existing state-of-the-art models, marking a substantial step forward in effective archival data management. Ultimately, ArcGPT aims to better serve the archival community, aiding archivists in their crucial role of preserving and harnessing our collective information and knowledge.
Authors: Jihyeon Lee, Dain Kim, Doohae Jung, Boseop Kim, Kyoung-Woon On
In-context learning, which offers substantial advantages over fine-tuning, is predominantly observed in decoder-only models, while encoder-decoder (i.e., seq2seq) models excel in methods that rely on weight updates. Recently, a few studies have demonstrated the feasibility of few-shot learning with seq2seq models; however, this has been limited to tasks that align well with the seq2seq architecture, such as summarization and translation. Inspired by these initial studies, we provide a first-ever extensive experiment comparing the in-context few-shot learning capabilities of decoder-only and encoder-decoder models on a broad range of tasks. Furthermore, we propose two methods to more effectively elicit in-context learning ability in seq2seq models: objective-aligned prompting and a fusion-based approach. Remarkably, our approach outperforms a decoder-only model that is six times larger and exhibits significant performance improvements compared to conventional seq2seq models across a variety of settings. We posit that, with the right configuration and prompt design, seq2seq models can be highly effective few-shot learners for a wide spectrum of applications.
Authors: Yangning Li, Tingwei Lu, Yinghui Li, Tianyu Yu, Shulin Huang, Hai-Tao Zheng, Rui Zhang, Jun Yuan
The Entity Set Expansion (ESE) task aims to expand a handful of seed entities with new entities belonging to the same semantic class. Conventional ESE methods are based on mono-modality (i.e., literal modality), which struggle to deal with complex entities in the real world such as: (1) Negative entities with fine-grained semantic differences. (2) Synonymous entities. (3) Polysemous entities. (4) Long-tailed entities. These challenges prompt us to propose Multi-modal Entity Set Expansion (MESE), where models integrate information from multiple modalities to represent entities. Intuitively, the benefits of multi-modal information for ESE are threefold: (1) Different modalities can provide complementary information. (2) Multi-modal information provides a unified signal via common visual properties for the same semantic class or entity. (3) Multi-modal information offers robust alignment signal for synonymous entities. To assess the performance of model in MESE and facilitate further research, we constructed the MESED dataset which is the first multi-modal dataset for ESE with large-scale and elaborate manual calibration. A powerful multi-modal model MultiExpan is proposed which is pre-trained on four multimodal pre-training tasks. The extensive experiments and analyses on MESED demonstrate the high quality of the dataset and the effectiveness of our MultiExpan, as well as pointing the direction for future research.
Authors: Sareh Ahmadi, Aditya Shah, Edward Fox
This paper addresses the problem of selecting of a set of texts for annotation in text classification using retrieval methods when there are limits on the number of annotations due to constraints on human resources. An additional challenge addressed is dealing with binary categories that have a small number of positive instances, reflecting severe class imbalance. In our situation, where annotation occurs over a long time period, the selection of texts to be annotated can be made in batches, with previous annotations guiding the choice of the next set. To address these challenges, the paper proposes leveraging SHAP to construct a quality set of queries for Elasticsearch and semantic search, to try to identify optimal sets of texts for annotation that will help with class imbalance. The approach is tested on sets of cue texts describing possible future events, constructed by participants involved in studies aimed to help with the management of obesity and diabetes. We introduce an effective method for selecting a small set of texts for annotation and building high-quality classifiers. We integrate vector search, semantic search, and machine learning classifiers to yield a good solution. Our experiments demonstrate improved F1 scores for the minority classes in binary classification.
Authors: Umitcan Sahin, Izzet Emre Kucukkaya, Cagri Toraman
Fanfiction, a popular form of creative writing set within established fictional universes, has gained a substantial online following. However, ensuring the well-being and safety of participants has become a critical concern in this community. The detection of triggering content, material that may cause emotional distress or trauma to readers, poses a significant challenge. In this paper, we describe our approach for the Trigger Detection shared task at PAN CLEF 2023, where we want to detect multiple triggering content in a given Fanfiction document. For this, we build a hierarchical model that uses recurrence over Transformer-based language models. In our approach, we first split long documents into smaller sized segments and use them to fine-tune a Transformer model. Then, we extract feature embeddings from the fine-tuned Transformer model, which are used as input in the training of multiple LSTM models for trigger detection in a multi-label setting. Our model achieves an F1-macro score of 0.372 and F1-micro score of 0.736 on the validation set, which are higher than the baseline results shared at PAN CLEF 2023.
Authors: Izzet Emre Kucukkaya, Umitcan Sahin, Cagri Toraman
The task of multi-author writing style detection aims at finding any positions of writing style change in a given text document. We formulate the task as a natural language inference problem where two consecutive paragraphs are paired. Our approach focuses on transitions between paragraphs while truncating input tokens for the task. As backbone models, we employ different Transformer-based encoders with warmup phase during training. We submit the model version that outperforms baselines and other proposed model versions in our experiments. For the easy and medium setups, we submit transition-focused natural language inference based on DeBERTa with warmup training, and the same model without transition for the hard setup.
Authors: Bo Shen, Jiaxin Zhang, Taihong Chen, Daoguang Zan, Bing Geng, An Fu, Muhan Zeng, Ailun Yu, Jichuan Ji, Jingyang Zhao, Yuenan Guo, Qianxiang Wang
Large Language Models for Code (Code LLM) are flourishing. New and powerful models are released on a weekly basis, demonstrating remarkable performance on the code generation task. Various approaches have been proposed to boost the code generation performance of pre-trained Code LLMs, such as supervised fine-tuning, instruction tuning, reinforcement learning, etc. In this paper, we propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation. Under this framework, we present PanGu-Coder2, which achieves 62.20% pass@1 on the OpenAI HumanEval benchmark. Furthermore, through an extensive evaluation on CoderEval and LeetCode benchmarks, we show that PanGu-Coder2 consistently outperforms all previous Code LLMs.
Authors: Or Sharir, Anima Anandkumar
Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited. Re-running the model each time is expensive, even with compression techniques like knowledge distillation, pruning, or quantization. Instead, we take an incremental computing approach, looking to reuse calculations as the inputs change. However, the dense connectivity of conventional architectures poses a major obstacle to incremental computation, as even minor input changes cascade through the network and restrict information reuse. To address this, we use vector quantization to discretize intermediate values in the network, which filters out noisy and unnecessary modifications to hidden neurons, facilitating the reuse of their values. We apply this approach to the transformers architecture, creating an efficient incremental inference algorithm with complexity proportional to the fraction of the modified inputs. Our experiments with adapting the OPT-125M pre-trained language model demonstrate comparable accuracy on document classification while requiring 12.1X (median) fewer operations for processing sequences of atomic edits.
Authors: Zhen Qin, Dong Li, Weigao Sun, Weixuan Sun, Xuyang Shen, Xiaodong Han, Yunshen Wei, Baohong Lv, Fei Yuan, Xiao Luo, Yu Qiao, Yiran Zhong
We present TransNormerLLM, the first linear attention-based Large Language Model (LLM) that outperforms conventional softmax attention-based models in terms of both accuracy and efficiency. TransNormerLLM evolves from the previous linear attention architecture TransNormer by making advanced modifications that include positional embedding, linear attention acceleration, gating mechanism, tensor normalization, inference acceleration and stabilization. Specifically, we use LRPE together with an exponential decay to avoid attention dilution issues while allowing the model to retain global interactions between tokens. Additionally, we propose Lightning Attention, a cutting-edge technique that accelerates linear attention by more than twice in runtime and reduces memory usage by a remarkable four times. To further enhance the performance of TransNormer, we leverage a gating mechanism to smooth training and a new tensor normalization scheme to accelerate the model, resulting in an impressive acceleration of over 20%. Furthermore, we have developed a robust inference algorithm that ensures numerical stability and consistent inference speed, regardless of the sequence length, showcasing superior efficiency during both training and inference stages. Scalability is at the heart of our model's design, enabling seamless deployment on large-scale clusters and facilitating expansion to even more extensive models, all while maintaining outstanding performance metrics. Rigorous validation of our model design is achieved through a series of comprehensive experiments on our self-collected corpus, boasting a size exceeding 6TB and containing over 2 trillion tokens. To ensure data quality and relevance, we implement a new self-cleaning strategy to filter our collected data. Our pre-trained models will be released to foster community advancements in efficient LLMs.
Authors: Juri Opitz
The effectiveness of compression distance in KNN-based text classification ('gzip') has recently garnered lots of attention. In this note, we show that similar or better effectiveness can be achieved with simpler means, and text compression may not be necessary. Indeed, we find that a simple 'bag-of-words' matching can achieve similar or better accuracy, and is more efficient.
Authors: Liang Xu, Anqi Li, Lei Zhu, Hang Xue, Changtai Zhu, Kangkang Zhao, Haonan He, Xuanwei Zhang, Qiyue Kang, Zhenzhong Lan
Large language models (LLMs) have shown the potential to be integrated into human daily lives. Therefore, user preference is the most critical criterion for assessing LLMs' performance in real-world scenarios. However, existing benchmarks mainly focus on measuring models' accuracy using multi-choice questions, which limits the understanding of their capabilities in real applications. We fill this gap by proposing a comprehensive Chinese benchmark SuperCLUE, named after another popular Chinese LLM benchmark CLUE. SuperCLUE encompasses three sub-tasks: actual users' queries and ratings derived from an LLM battle platform (CArena), open-ended questions with single and multiple-turn dialogues (OPEN), and closed-ended questions with the same stems as open-ended single-turn ones (CLOSE). Our study shows that accuracy on closed-ended questions is insufficient to reflect human preferences achieved on open-ended ones. At the same time, they can complement each other to predict actual user preferences. We also demonstrate that GPT-4 is a reliable judge to automatically evaluate human preferences on open-ended questions in a Chinese context. Our benchmark will be released at https://www.CLUEbenchmarks.com
Authors: Andy Zou, Zifan Wang, J. Zico Kolter, Matt Fredrikson
Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some success at circumventing these measures -- so-called "jailbreaks" against LLMs -- these attacks have required significant human ingenuity and are brittle in practice. In this paper, we propose a simple and effective attack method that causes aligned language models to generate objectionable behaviors. Specifically, our approach finds a suffix that, when attached to a wide range of queries for an LLM to produce objectionable content, aims to maximize the probability that the model produces an affirmative response (rather than refusing to answer). However, instead of relying on manual engineering, our approach automatically produces these adversarial suffixes by a combination of greedy and gradient-based search techniques, and also improves over past automatic prompt generation methods.
Surprisingly, we find that the adversarial prompts generated by our approach are quite transferable, including to black-box, publicly released LLMs. Specifically, we train an adversarial attack suffix on multiple prompts (i.e., queries asking for many different types of objectionable content), as well as multiple models (in our case, Vicuna-7B and 13B). When doing so, the resulting attack suffix is able to induce objectionable content in the public interfaces to ChatGPT, Bard, and Claude, as well as open source LLMs such as LLaMA-2-Chat, Pythia, Falcon, and others. In total, this work significantly advances the state-of-the-art in adversarial attacks against aligned language models, raising important questions about how such systems can be prevented from producing objectionable information. Code is available at github.com/llm-attacks/llm-attacks.
Authors: Qiao Jin, Zifeng Wang, Charalampos S. Floudas, Jimeng Sun, Zhiyong Lu
Clinical trials are vital in advancing drug development and evidence-based medicine, but their success is often hindered by challenges in patient recruitment. In this work, we investigate the potential of large language models (LLMs) to assist individual patients and referral physicians in identifying suitable clinical trials from an extensive selection. Specifically, we introduce TrialGPT, a novel architecture employing LLMs to predict criterion-level eligibility with detailed explanations, which are then aggregated for ranking and excluding candidate clinical trials based on free-text patient notes. We evaluate TrialGPT on three publicly available cohorts of 184 patients and 18,238 annotated clinical trials. The experimental results demonstrate several key findings: First, TrialGPT achieves high criterion-level prediction accuracy with faithful explanations. Second, the aggregated trial-level TrialGPT scores are highly correlated with expert eligibility annotations. Third, these scores prove effective in ranking clinical trials and exclude ineligible candidates. Our error analysis suggests that current LLMs still make some mistakes due to limited medical knowledge and domain-specific context understanding. Nonetheless, we believe the explanatory capabilities of LLMs are highly valuable. Future research is warranted on how such AI assistants can be integrated into the routine trial matching workflow in real-world settings to improve its efficiency.
Authors: Clément Guerner, Anej Svete, Tianyu Liu, Alexander Warstadt, Ryan Cotterell
Large language models rely on real-valued representations of text to make their predictions. These representations contain information learned from the data that the model has trained on, including knowledge of linguistic properties and forms of demographic bias, e.g., based on gender. A growing body of work has considered information about concepts such as these using orthogonal projections onto subspaces of the representation space. We contribute to this body of work by proposing a formal definition of intrinsic information in a subspace of a language model's representation space. We propose a counterfactual approach that avoids the failure mode of spurious correlations (Kumar et al., 2022) by treating components in the subspace and its orthogonal complement independently. We show that our counterfactual notion of information in a subspace is optimizing by an causal concept subspace. Furthermore, this intervention allows us to attempt concept controlled generation by manipulating the value of the conceptual component of a representation. Empirically, we find that R-LACE (Ravfogel et al., 2022) returns a one-dimensional subspace containing roughly half of total concept information under our framework. Our causal controlled intervention shows that, for at least one model, the subspace returned by R-LACE can be used to manipulate the concept value of the generated word with precision.
Authors: Jiaoda Li, Ryan Cotterell, Mrinmaya Sachan
Multi-head attention, a collection of several attention mechanisms that independently attend to different parts of the input, is the key ingredient in the Transformer. Recent work has shown, however, that a large proportion of the heads in a Transformer's multi-head attention mechanism can be safely pruned away without significantly harming the performance of the model; such pruning leads to models that are noticeably smaller and faster in practice. Our work introduces a new head pruning technique that we term differentiable subset pruning. Intuitively, our method learns per-head importance variables and then enforces a user-specified hard constraint on the number of unpruned heads. The importance variables are learned via stochastic gradient descent. We conduct experiments on natural language inference and machine translation; we show that differentiable subset pruning performs comparably or better than previous works while offering precise control of the sparsity level.
Authors: Xiang Chen, Lei Li, Ningyu Zhang, Xiaozhuan Liang, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen
Prompt learning approaches have made waves in natural language processing by inducing better few-shot performance while they still follow a parametric-based learning paradigm; the oblivion and rote memorization problems in learning may encounter unstable generalization issues. Specifically, vanilla prompt learning may struggle to utilize atypical instances by rote during fully-supervised training or overfit shallow patterns with low-shot data. To alleviate such limitations, we develop RetroPrompt with the motivation of decoupling knowledge from memorization to help the model strike a balance between generalization and memorization. In contrast with vanilla prompt learning, RetroPrompt constructs an open-book knowledge-store from training instances and implements a retrieval mechanism during the process of input, training and inference, thus equipping the model with the ability to retrieve related contexts from the training corpus as cues for enhancement. Extensive experiments demonstrate that RetroPrompt can obtain better performance in both few-shot and zero-shot settings. Besides, we further illustrate that our proposed RetroPrompt can yield better generalization abilities with new datasets. Detailed analysis of memorization indeed reveals RetroPrompt can reduce the reliance of language models on memorization; thus, improving generalization for downstream tasks. Code is available in https://github.com/zjunlp/PromptKG/tree/main/research/RetroPrompt.
Authors: Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, Colin Raffel
The Internet contains a wealth of knowledge -- from the birthdays of historical figures to tutorials on how to code -- all of which may be learned by language models. However, while certain pieces of information are ubiquitous on the web, others appear extremely rarely. In this paper, we study the relationship between the knowledge memorized by large language models and the information in pre-training datasets scraped from the web. In particular, we show that a language model's ability to answer a fact-based question relates to how many documents associated with that question were seen during pre-training. We identify these relevant documents by entity linking pre-training datasets and counting documents that contain the same entities as a given question-answer pair. Our results demonstrate strong correlational and causal relationships between accuracy and relevant document count for numerous question answering datasets (e.g., TriviaQA), pre-training corpora (e.g., ROOTS), and model sizes (e.g., 176B parameters). Moreover, while larger models are better at learning long-tail knowledge, we estimate that today's models must be scaled by many orders of magnitude to reach competitive QA performance on questions with little support in the pre-training data. Finally, we show that retrieval-augmentation can reduce the dependence on relevant pre-training information, presenting a promising approach for capturing the long-tail.
Authors: Simon Ott, Konstantin Hebenstreit, Valentin Liévin, Christoffer Egeberg Hother, Milad Moradi, Maximilian Mayrhauser, Robert Praas, Ole Winther, Matthias Samwald
Large language models (LLMs) such as GPT-4 have recently demonstrated impressive results across a wide range of tasks. LLMs are still limited, however, in that they frequently fail at complex reasoning, their reasoning processes are opaque, they are prone to 'hallucinate' facts, and there are concerns about their underlying biases. Letting models verbalize reasoning steps as natural language, a technique known as chain-of-thought prompting, has recently been proposed as a way to address some of these issues. Here we present ThoughtSource, a meta-dataset and software library for chain-of-thought (CoT) reasoning. The goal of ThoughtSource is to improve future artificial intelligence systems by facilitating qualitative understanding of CoTs, enabling empirical evaluations, and providing training data. This first release of ThoughtSource integrates seven scientific/medical, three general-domain and five math word question answering datasets.
Authors: Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham
Retrieval-Augmented Language Modeling (RALM) methods, which condition a language model (LM) on relevant documents from a grounding corpus during generation, were shown to significantly improve language modeling performance. In addition, they can mitigate the problem of factually inaccurate text generation and provide natural source attribution mechanism. Existing RALM approaches focus on modifying the LM architecture in order to facilitate the incorporation of external information, significantly complicating deployment. This paper considers a simple alternative, which we dub In-Context RALM: leaving the LM architecture unchanged and prepending grounding documents to the input, without any further training of the LM. We show that In-Context RALM that builds on off-the-shelf general purpose retrievers provides surprisingly large LM gains across model sizes and diverse corpora. We also demonstrate that the document retrieval and ranking mechanism can be specialized to the RALM setting to further boost performance. We conclude that In-Context RALM has considerable potential to increase the prevalence of LM grounding, particularly in settings where a pretrained LM must be used without modification or even via API access.
Authors: Limao Xiong, Jie Zhou, Qunxi Zhu, Xiao Wang, Yuanbin Wu, Qi Zhang, Tao Gui, Xuanjing Huang, Jin Ma, Ying Shan
Existing models for named entity recognition (NER) are mainly based on large-scale labeled datasets, which always obtain using crowdsourcing. However, it is hard to obtain a unified and correct label via majority voting from multiple annotators for NER due to the large labeling space and complexity of this task. To address this problem, we aim to utilize the original multi-annotator labels directly. Particularly, we propose a Confidence-based Partial Label Learning (CPLL) method to integrate the prior confidence (given by annotators) and posterior confidences (learned by models) for crowd-annotated NER. This model learns a token- and content-dependent confidence via an Expectation-Maximization (EM) algorithm by minimizing empirical risk. The true posterior estimator and confidence estimator perform iteratively to update the true posterior and confidence respectively. We conduct extensive experimental results on both real-world and synthetic datasets, which show that our model can improve performance effectively compared with strong baselines.
Authors: Evangelos Pournaras
Large language models of artificial intelligence (AI), such as ChatGPT, find remarkable but controversial applicability in science and research. This paper reviews epistemological challenges, ethical and integrity risks in science conduct in the advent of generative AI. This is with the aim to lay new timely foundations for a high-quality research ethics review. The role of AI language models as a research instrument and subject is scrutinized along with ethical implications for scientists, participants and reviewers. New emerging practices for research ethics review are discussed, concluding with ten recommendations that shape a response for a more responsible research conduct in the era of AI.
Authors: Loukas Ilias, Dimitris Askounis
Alzheimer's disease (AD) constitutes a complex neurocognitive disease and is the main cause of dementia. Although many studies have been proposed targeting at diagnosing dementia through spontaneous speech, there are still limitations. Existing state-of-the-art approaches, which propose multimodal methods, train separately language and acoustic models, employ majority-vote approaches, and concatenate the representations of the different modalities either at the input level, i.e., early fusion, or during training. Also, some of them employ self-attention layers, which calculate the dependencies between representations without considering the contextual information. In addition, no prior work has taken into consideration the model calibration. To address these limitations, we propose some new methods for detecting AD patients, which capture the intra- and cross-modal interactions. First, we convert the audio files into log-Mel spectrograms, their delta, and delta-delta and create in this way an image per audio file consisting of three channels. Next, we pass each transcript and image through BERT and DeiT models respectively. After that, context-based self-attention layers, self-attention layers with a gate model, and optimal transport domain adaptation methods are employed for capturing the intra- and inter-modal interactions. Finally, we exploit two methods for fusing the self and cross-attention features. For taking into account the model calibration, we apply label smoothing. We use both performance and calibration metrics. Experiments conducted on the ADReSS and ADReSSo Challenge datasets indicate the efficacy of our introduced approaches over existing research initiatives with our best performing model reaching Accuracy and F1-score up to 91.25% and 91.06% respectively.
Authors: Maximilian Wegge, Roman Klinger
The most prominent subtask in emotion analysis is emotion classification; to assign a category to a textual unit, for instance a social media post. Many research questions from the social sciences do, however, not only require the detection of the emotion of an author of a post but to understand who is ascribed an emotion in text. This task is tackled by emotion role labeling which aims at extracting who is described in text to experience an emotion, why, and towards whom. This could, however, be considered overly sophisticated if the main question to answer is who feels which emotion. A targeted approach for such setup is to classify emotion experiencer mentions (aka "emoters") regarding the emotion they presumably perceive. This task is similar to named entity recognition of person names with the difference that not every mentioned entity name is an emoter. While, very recently, data with emoter annotations has been made available, no experiments have yet been performed to detect such mentions. With this paper, we provide baseline experiments to understand how challenging the task is. We further evaluate the impact on experiencer-specific emotion categorization and appraisal detection in a pipeline, when gold mentions are not available. We show that experiencer detection in text is a challenging task, with a precision of .82 and a recall of .56 (F1 =.66). These results motivate future work of jointly modeling emoter spans and emotion/appraisal predictions.
Authors: Faeze Brahman, Chandra Bhagavatula, Valentina Pyatkin, Jena D. Hwang, Xiang Lorraine Li, Hirona J. Arai, Soumya Sanyal, Keisuke Sakaguchi, Xiang Ren, Yejin Choi
Procedural planning, which entails decomposing a high-level goal into a sequence of temporally ordered steps, is an important yet intricate task for machines. It involves integrating common-sense knowledge to reason about complex contextualized situations that are often counterfactual, e.g. "scheduling a doctor's appointment without a phone". While current approaches show encouraging results using large language models (LLMs), they are hindered by drawbacks such as costly API calls and reproducibility issues. In this paper, we advocate planning using smaller language models. We present PlaSma, a novel two-pronged approach to endow small language models with procedural knowledge and (counterfactual) planning capabilities. More concretely, we develop symbolic procedural knowledge distillation to enhance the implicit knowledge in small language models and an inference-time algorithm to facilitate more structured and accurate reasoning. In addition, we introduce a novel task, Counterfactual Planning, that requires a revision of a plan to cope with a counterfactual situation. In both the original and counterfactual setting, we show that orders-of-magnitude smaller models (770M-11B parameters) can compete and often surpass their larger teacher models' capabilities.
Authors: Walid S. Saba
Large language models (LLMs) have achieved a milestone that undenia-bly changed many held beliefs in artificial intelligence (AI). However, there remains many limitations of these LLMs when it comes to true language understanding, limitations that are a byproduct of the under-lying architecture of deep neural networks. Moreover, and due to their subsymbolic nature, whatever knowledge these models acquire about how language works will always be buried in billions of microfeatures (weights), none of which is meaningful on its own, making such models hopelessly unexplainable. To address these limitations, we suggest com-bining the strength of symbolic representations with what we believe to be the key to the success of LLMs, namely a successful bottom-up re-verse engineering of language at scale. As such we argue for a bottom-up reverse engineering of language in a symbolic setting. Hints on what this project amounts to have been suggested by several authors, and we discuss in some detail here how this project could be accomplished.
Authors: Raphael Frick, Inna Vogel
The option of sharing images, videos and audio files on social media opens up new possibilities for distinguishing between false information and fake news on the Internet. Due to the vast amount of data shared every second on social media, not all data can be verified by a computer or a human expert. Here, a check-worthiness analysis can be used as a first step in the fact-checking pipeline and as a filtering mechanism to improve efficiency. This paper proposes a novel way of detecting the check-worthiness in multi-modal tweets. It takes advantage of two classifiers, each trained on a single modality. For image data, extracting the embedded text with an OCR analysis has shown to perform best. By combining the two classifiers, the proposed solution was able to place first in the CheckThat! 2023 Task 1A with an F1 score of 0.7297 achieved on the private test set.
Authors: Shuzheng Si, Shuang Zeng, Baobao Chang
Incomplete utterance rewriting has recently raised wide attention. However, previous works do not consider the semantic structural information between incomplete utterance and rewritten utterance or model the semantic structure implicitly and insufficiently. To address this problem, we propose a QUEry-Enhanced Network (QUEEN). Firstly, our proposed query template explicitly brings guided semantic structural knowledge between the incomplete utterance and the rewritten utterance making model perceive where to refer back to or recover omitted tokens. Then, we adopt a fast and effective edit operation scoring network to model the relation between two tokens. Benefiting from proposed query template and the well-designed edit operation scoring network, QUEEN achieves state-of-the-art performance on several public datasets.
Authors: Raphael Frick, Inna Vogel, Jeong-Eun Choi
This paper describes the second-placed approach developed by the Fraunhofer SIT team in the CLEF-2023 CheckThat! lab Task 1B for English. Given a text snippet from a political debate, the aim of this task is to determine whether it should be assessed for check-worthiness. Detecting check-worthy statements aims to facilitate manual fact-checking efforts by prioritizing the claims that fact-checkers should consider first. It can also be considered as primary step of a fact-checking system. Our best-performing method took advantage of an ensemble classification scheme centered on Model Souping. When applied to the English data set, our submitted model achieved an overall F1 score of 0.878 and was ranked as the second-best model in the competition.
Authors: Yu Ji, Wen Wu, Hong Zheng, Yi Hu, Xi Chen, Liang He
In recent years, personality has been regarded as a valuable personal factor being incorporated into numerous tasks such as sentiment analysis and product recommendation. This has led to widespread attention to text-based personality recognition task, which aims to identify an individual's personality based on given text. Considering that ChatGPT has recently exhibited remarkable abilities on various natural language processing tasks, we provide a preliminary evaluation of ChatGPT on text-based personality recognition task for generating effective personality data. Concretely, we employ a variety of prompting strategies to explore ChatGPT's ability in recognizing personality from given text, especially the level-oriented prompting strategy we designed for guiding ChatGPT in analyzing given text at a specified level. The experimental results on two representative real-world datasets reveal that ChatGPT with zero-shot chain-of-thought prompting exhibits impressive personality recognition ability and is capable to provide natural language explanations through text-based logical reasoning. Furthermore, by employing the level-oriented prompting strategy to optimize zero-shot chain-of-thought prompting, the performance gap between ChatGPT and corresponding state-of-the-art model has been narrowed even more. However, we observe that ChatGPT shows unfairness towards certain sensitive demographic attributes such as gender and age. Additionally, we discover that eliciting the personality recognition ability of ChatGPT helps improve its performance on personality-related downstream tasks such as sentiment classification and stress prediction.
Authors: Andrea Bacciu, Florin Cuconasu, Federico Siciliano, Fabrizio Silvestri, Nicola Tonellotto, Giovanni Trappolini
The emergence of large language models (LLMs) has revolutionized machine learning and related fields, showcasing remarkable abilities in comprehending, generating, and manipulating human language. However, their conventional usage through API-based text prompt submissions imposes certain limitations in terms of context constraints and external source availability. To address these challenges, we propose a novel framework called Reinforced Retrieval Augmented Machine Learning (RRAML). RRAML integrates the reasoning capabilities of LLMs with supporting information retrieved by a purpose-built retriever from a vast user-provided database. By leveraging recent advancements in reinforcement learning, our method effectively addresses several critical challenges. Firstly, it circumvents the need for accessing LLM gradients. Secondly, our method alleviates the burden of retraining LLMs for specific tasks, as it is often impractical or impossible due to restricted access to the model and the computational intensity involved. Additionally we seamlessly link the retriever's task with the reasoner, mitigating hallucinations and reducing irrelevant, and potentially damaging retrieved documents. We believe that the research agenda outlined in this paper has the potential to profoundly impact the field of AI, democratizing access to and utilization of LLMs for a wide range of entities.
Authors: Yifei Gao, Lei Wang, Jun Fang, Longhua Hu, Jun Cheng
Recently, with the emergence of numerous Large Language Models (LLMs), the implementation of AI has entered a new era. Irrespective of these models' own capacity and structure, there is a growing demand for LLMs to possess enhanced comprehension of longer and more complex contexts with relatively smaller sizes. Models often encounter an upper limit when processing sequences of sentences that extend beyond their comprehension capacity and result in off-topic or even chaotic responses. While several recent works attempt to address this issue in various ways, they rarely focus on "why models are unable to compensate or strengthen their capabilities on their own". In this paper, we thoroughly investigate the nature of information transfer within LLMs and propose a novel technique called Attention Transition. This technique empowers models to achieve longer and better context comprehension with minimal additional training or impact on generation fluency. Our experiments are conducted on the challenging XSum dataset using LLaMa-7b model with context token length ranging from 800 to 1900. Results demonstrate that we achieve substantial improvements compared with the original generation results evaluated by GPT4.
Authors: Zhengliang Liu, Tianyang Zhong, Yiwei Li, Yutong Zhang, Yi Pan, Zihao Zhao, Peixin Dong, Chao Cao, Yuxiao Liu, Peng Shu, Yaonai Wei, Zihao Wu, Chong Ma, Jiaqi Wang, Sheng Wang, Mengyue Zhou, Zuowei Jiang, Chunlin Li, Jason Holmes, Shaochen Xu, Lu Zhang, Haixing Dai, Kai Zhang, Lin Zhao, Yuanhao Chen, Xu Liu, Peilong Wang, Pingkun Yan, Jun Liu, Bao Ge, Lichao Sun, Dajiang Zhu, Xiang Li, Wei Liu, Xiaoyan Cai, Xintao Hu, Xi Jiang, Shu Zhang, Xin Zhang, Tuo Zhang, Shijie Zhao, Quanzheng Li, Hongtu Zhu, Dinggang Shen, Tianming Liu
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP). LLMs have revolutionized a multitude of domains, and they have made a significant impact in the medical field. Large language models are now more abundant than ever, and many of these models exhibit bilingual capabilities, proficient in both English and Chinese. However, a comprehensive evaluation of these models remains to be conducted. This lack of assessment is especially apparent within the context of radiology NLP. This study seeks to bridge this gap by critically evaluating thirty two LLMs in interpreting radiology reports, a crucial component of radiology NLP. Specifically, the ability to derive impressions from radiologic findings is assessed. The outcomes of this evaluation provide key insights into the performance, strengths, and weaknesses of these LLMs, informing their practical applications within the medical domain.
Authors: Tian-Hao Zhang, Dinghao Zhou, Guiping Zhong, Baoxiang Li
RNN-T models are widely used in ASR, which rely on the RNN-T loss to achieve length alignment between input audio and target sequence. However, the implementation complexity and the alignment-based optimization target of RNN-T loss lead to computational redundancy and a reduced role for predictor network, respectively. In this paper, we propose a novel model named CIF-Transducer (CIF-T) which incorporates the Continuous Integrate-and-Fire (CIF) mechanism with the RNN-T model to achieve efficient alignment. In this way, the RNN-T loss is abandoned, thus bringing a computational reduction and allowing the predictor network a more significant role. We also introduce Funnel-CIF, Context Blocks, Unified Gating and Bilinear Pooling joint network, and auxiliary training strategy to further improve performance. Experiments on the 178-hour AISHELL-1 and 10000-hour WenetSpeech datasets show that CIF-T achieves state-of-the-art results with lower computational overhead compared to RNN-T models.