This study evaluates the proficiency of Large Language Models (LLMs) in accurately labeling clinical document excerpts. Our focus is on the assignment of potential or confirmed diagnoses and medical procedures to snippets of medical text sourced from unstructured clinical patient records. We explore how the performance of LLMs compare against human annotators in classifying these excerpts. Employing a few-shot, chain-of-thought prompting approach with the MIMIC-III dataset, Med-PaLM 2 showcases annotation accuracy comparable to human annotators, achieving a notable precision rate of approximately 92% relative to the gold standard labels established by human experts.

Soccer is a globally popular sport with a vast audience, in this paper, we consider constructing an automatic soccer game commentary model to improve the audiences’ viewing experience. In general, we make the following contributions: *First*, observing the prevalent video-text misalignment in existing datasets, we manually annotate timestamps for 49 matches, establishing a more robust benchmark for soccer game commentary generation, termed as *SN-Caption-test-align*; *Second*, we propose a multi-modal temporal alignment pipeline to automatically correct and filter the existing dataset at scale, creating a higher-quality soccer game commentary dataset for training, denoted as *MatchTime*; *Third*, based on our curated dataset, we train an automatic commentary generation model, named **MatchVoice**. Extensive experiments and ablation studies have demonstrated the effectiveness of our alignment pipeline, and training model on the curated datasets achieves state-of-the-art performance for commentary generation, showcasing that better alignment can lead to significant performance improvements in downstream tasks.

Given a sentence and a particular aspect term, aspect-based sentiment analysis (ABSA) aims to predict the sentiment polarity towards this aspect term, which provides fine-grained analysis on sentiment understanding and it has attracted much attention in recent years. In order to achieve a good performance on ABSA, it is important for a model to appropriately encode contextual information, especially identifying salient features and eliminating noise in the context. To make incorrect predictions, most existing approaches employ powerful text encoders to locate important context features, as well as noises that mislead ABSA models. These approaches determine the noise in the text for ABSA by assigning low weights to context features or directly removing them from model input, which runs the risk of computing wrong weights or eliminating important context information. In this paper, we propose to improve ABSA with context denoising, where three types of word-level information are regarded as noise, namely, lexicographic noise, bag-of-words noise, and syntax noise. We utilize diffusion networks to perform the denoising process to gradually eliminate them so as to better predict sentiment polarities for given aspect terms. Our approach uses task-specific noise rather than the standard stochastic Gaussian noise in the diffusion networks. The experimental results on five widely used ABSA datasets demonstrate the validity and effectiveness of our approach.

Recent advances in large language models (LLMs) have led to significant success in using LLMs as agents. Nevertheless, a common assumption that LLMs always process honest information neglects the widespread deceptive or misleading content in human and AI-generated material. This oversight might expose LLMs to malicious manipulations. To enhance LLMs’ ability to identify and counteract deceptive information, in this paper, inspired by humans’ recursive thinking and perspective-taking, we introduce a novel cognitive framework, Recursive Contemplation (ReCon). ReCon combines formulation and refinement contemplation processes; formulation contemplation produces initial thoughts and speech, while refinement contemplation further polishes them. Additionally, we incorporate first-order and second-order perspective transitions into these processes respectively. Specifically, the first-order allows an LLM agent to infer others’ mental states, and the second-order involves understanding how others perceive the agent’s mental state. After integrating ReCon with various LLMs, extensive experiment results from the Avalon game and BigTom benchmark indicate ReCon’s efficacy in aiding LLMs to discern and maneuver around deceptive information without extra fine-tuning and data. Finally, we demonstrate ReCon’s scaling trend with model parameters, and explore the current limitations of LLMs in terms of safety and reasoning, potentially furnishing insights for subsequent research. Our project page can be found at https://shenzhi-wang.github.io/avalon_recon.

To improve the performance of the dual-encoder retriever, one effective approach is knowledge distillation from the cross-encoder ranker. Existing works prepare training instances by pairing each query with one positive and a batch of negatives. However, most hard negatives mined by advanced dense retrieval methods are still too trivial for the teacher to distinguish, preventing the teacher from transferring abundant dark knowledge to the student through its soft label. To alleviate this issue, we propose Adam, a knowledge distillation framework that can better transfer the dark knowledge held in the teacher with adaptive dark examples. Different from previous works that only rely on one positive and hard negatives as candidate passages, we create dark examples that all have moderate relevance to the query by strengthening negatives and masking positives in the discrete space. Furthermore, as the quality of knowledge held in different training instances varies as measured by the teacher’s confidence score, we propose a self-paced distillation strategy that adaptively concentrates on a subset of high-quality instances to conduct our dark-example-based knowledge distillation to help the student learn better. We conduct experiments on two widely-used benchmarks and verify the effectiveness of our method.

La Direction Marketing de SNCF Voyageurs INTERCITÉS souhaite améliorer l’expérience des voyageurs en procédant à l’analyse automatique de la perception de son offre à travers les ressentis partagés sur les réseaux sociaux. L’un des axes de notre recherche se focalise sur la détection des émotions en multi-étiquettes qui traduisent cette perception. Pour accomplir cette tâche, nous ajustons tout d’abord un modèle de langue pré-entraîné à l’aide d’un corpus préalablement annoté en émotions, puis nous le spécialisons sur notre corpus, axé sur le contexte ferroviaire d’INTERCITÉS. Notre approche obtient un F1-Micro score de 0,55, un F1-Macro score de 0,44 et une exactitude de 0,826.

Cet article décrit la participation de l’équipe Sorbonne-SNCF au Défi Fouille de Textes 2024, se concentrant sur la correction automatique de QCM en langue française. Le corpus, constitué de questions de pharmacologie, a été reformulé en assertions. Nous avons employé des techniques avancées de traitement du langage naturel pour traiter les réponses. Trois approches principales, NachosLLM, TTGV byfusion, et TTGV ollama multilabel, sont présentées avec des scores EMR respectifs de 2.94, 4.19 et 1.68. Les résultats obtenus montrent des niveaux de précision différents, en soulignant les limites des approches multi-étiquettes. Des suggestions d’amélioration incluent l’ajustement des modèles de langage et des critères de classification.

Topic model is a statistical model that leverages unsupervised learning to mine hidden topics in document collections. The data sparsity and colloquialism of social texts make it difficult to accurately mine the topics. Traditional methods assume that there are only 0/1-state relationships between the two parties in the social networks, but the relationship status in real life is more complicated, such as continuously changing relationships with different degrees of intimacy. This paper proposes a continuous relational diffusion driven topic model (CRTM) with multi-grained text for microblog to realize the continuous representation of the relationship state and make up for the context and structural information lost by previous representation methods. Multi-grained text representation learning distinguishes the impact of formal and informal expression on the topics further and alleviates colloquialism problems. Specifically, based on the original social network, the reconstructed social network with continuous relationship status is obtained by using information diffusion technology. The graph convolution model is utilized to learn node embeddings through the new social network. Finally, the neural variational inference is applied to generate topics according to continuous relationships. We validate CRTM on three real datasets, and the experimental results show the effectiveness of the scheme.

Multi-level implicit discourse relation recognition (MIDRR) is a challenging task to recognize the hierarchical discourse relations between the arguments with the absence of connectives. Recent methods tend to incorporate the static hierarchical structure containing all senses (defined as global hierarchy) into prompt tuning through a path prompt template or hierarchical label refining. Howerver, hierarchical modeling is independent of the verbalizer, resulting in a failure to effectively utilize the output probability distribution information of verbalizer. Besides, they ignore the utilization of the dynamic hierarchical label sequence for each instance (defined as local hierarchy) in prompt tuning. In this paper, we propose a global and local hierarchical prompt tuning (GLHPT) framework, which utilize prior knowledge of PLMs while better incorporating hierarchical information from two aspects. We leverage bottom-up propagated probability as the global hierarchy to inject it into multi-level verbalizer (MLV). Furthermore, we design a local hierarchy-driven contrastive learning (LHCL) to improve the probability distribution of MLV. Finally, our model achieves competitive results on two benchmacks.

Electronic health records (EHRs) serve as a digital repository storing comprehensive medical information about patients. Representation learning for EHRs plays a crucial role in healthcare applications. In this paper, we propose a Multimodal Heterogeneous Graph-enhanced Representation Learning, denoted as MHGRL, aimed at learning effective EHR representations. To address the challenge posed by data insufficiency of EHRs, MHGRL utilizes a multimodal heterogeneous graph to model an EHR. Specifically, we construct a heterogeneous graph for each EHR and enrich it by incorporating multimodal information with medical ontology and textual notes. With the integration of pre-trained model, graph neural network, and attention mechanism, MHGRL effectively incorporates both node attributes and structural information across a multimodal heterogeneous graph. Moreover, we employ contrastive learning to ensure the consistency of representations for similar EHRs and improve the model robustness. The experimental results show that MHGRL outperforms all baselines on two real clinical datasets in downstream tasks, including EHR clustering and disease prediction. The code is available at https://github.com/emmali808/MHGRL.

Prompt-based fine-tuning (PF), by aligning with the training objective of pre-trained language models (PLMs), has shown improved performance on many few-shot natural language understanding (NLU) benchmarks. However, the word embedding space of PLMs exhibits anisotropy, which is called the representation degeneration problem. In this paper, we explore the self-similarity within the same context and identify the anisotropy of the feature embedding space in PF model. Given that the performance of PF models is dependent on feature embeddings, we inevitably pose the hypothesis: this anisotropy limits the performance of the PF models. Based on our experimental findings, we propose CLMA, a Contrastive Learning framework based on the [MASK] token and Answers, to alleviate the anisotropy in the embedding space. By combining our proposed counter-intuitive SSD, a Supervised Signal based on embedding Distance, our approach outperforms mainstream methods on the many NLU benchmarks in the few-shot experimental settings. In subsequent experiments, we analyze the capability of our method to capture deep semantic cues and the impact of the anisotropy in the feature embedding space on the performance of the PF model.

Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention. Recent common practice is to construct a two-stage pipeline with a fast retriever (e.g., bi-encoder) for first-stage recall followed by a smart response reranker (e.g., cross-encoder) for precise ranking. However, existing studies either optimize the retriever and reranker in independent ways, or distill the knowledge from a pre-trained reranker into the retriever in an asynchronous way, leading to sub-optimal performance of both modules. Thus, an open question remains about how to train them for a better combination of the best of both worlds. To this end, we present a cooperative training of the response retriever and the reranker whose parameters are dynamically optimized by the ground-truth labels as well as list-wise supervision signals from each other. As a result, the two modules can learn from each other and evolve together throughout the training. Experimental results on two benchmarks demonstrate the superiority of our method.

Event temporal relation extraction (ETRE) is usually formulated as a multi-label classification task, where each type of relation is simply treated as a one-hot label. This formulation ignores the meaning of relations and wipes out their intrinsic dependency. After examining the relation definitions in various ETRE tasks, we observe that all relations can be interpreted using the start and end time points of events. For example, relation Includes could be interpreted as event 1 starting no later than event 2 and ending no earlier than event 2. In this paper, we propose a unified event temporal relation extraction framework, which transforms temporal relations into logical expressions of time points and completes the ETRE by predicting the relations between certain time point pairs. Experiments on TB-Dense and MATRES show significant improvements over a strong baseline and outperform the state-of-the-art model by 0.3% on both datasets. By representing all relations in a unified framework, we can leverage the relations with sufficient data to assist the learning of other relations, thus achieving stable improvement in low-data scenarios. When the relation definitions are changed, our method can quickly adapt to the new ones by simply modifying the logic expressions that map time points to new event relations. The code is released at https://github.com/AndrewZhe/A-Unified-Framework-for-ETRE

Multi-hop reasoning, a prevalent approach for query answering, aims at inferring new facts along reasonable paths over a knowledge graph. Reinforcement learning methods can be adopted by formulating the problem into a Markov decision process. However, common suffering within RL-based reasoning models is that the agent can be biased to spurious paths which coincidentally lead to the correct answer with poor explanation. In this work, we take a deep dive into this phenomenon and define a metric named Path Spuriousness (PS), to quantitatively estimate to what extent a path is spurious. Guided by the definition of PS, we design a model with a new reward that considers both answer accuracy and path reasonableness. We test our method on four datasets and experiments reveal that our method considerably enhances the agent’s capacity to prevent spurious paths while keeping comparable to state-of-the-art performance.

Although the incorporation of pre-trained language models (PLMs) significantly pushes the research frontier of multi-turn response selection, it brings a new issue of heavy computation costs. To alleviate this problem and make the PLM-based response selection model both effective and efficient, we propose an inference framework together with a post-training strategy that builds upon any pre-trained transformer-based response selection models to accelerate inference by progressively selecting and eliminating unimportant content under the guidance of context-response dual-attention. Specifically, at each transformer layer, we first identify the importance of each word based on context-to-response and response-to-context attention, then select a number of unimportant words to be eliminated following a retention configuration derived from evolutionary search while passing the rest of the representations into deeper layers. To mitigate the training-inference gap posed by content elimination, we introduce a post-training strategy where we use knowledge distillation to force the model with progressively eliminated content to mimic the predictions of the original model with no content elimination. Experiments on three benchmarks indicate that our method can effectively speeds-up SOTA models without much performance degradation and shows a better trade-off between speed and performance than previous methods.

Pre-trained language models greatly improve the performance of various tasks but at a cost of high computation overhead. To facilitate practical applications, there are mainly two lines of research to accelerate model inference: model compression and dynamic computation (e.g., dynamic token pruning). Existing works either adopt these methods individually or simply apply dynamic computation approaches upon a compressed small language model. We argue that they are sub-optimal since the two approaches are separately designed so the compressed model may not be tailored for dynamic computation. To tackle this problem and make compressed small language models faster, we propose Length-Adaptive Distillation, a two-stage knowledge distillation framework that aims to produce a customized small language model for dynamic token pruning. In the general distillation stage, we enforce the student to mimic and reconstruct the teacher’s output based on the dynamically pruned representations. Then in the task-specific distillation stage, the student is further accustomed to token pruning while absorbing the task-specific knowledge. Experimental results on GLUE benchmark demonstrate that our method can make the small language model more customized for dynamic token pruning and achieve better speed-performance trade-off.

Recently, large language models (LLMs) have gained much attention for the emergence of human-comparable capabilities and huge potential. However, for open-domain implicit question-answering problems, LLMs may not be the ultimate solution due to the reasons of: 1) uncovered or out-of-date domain knowledge, 2) one-shot generation and hence restricted comprehensiveness. To this end, this work proposes a gradual knowledge excavation framework for open-domain complex question answering, where LLMs iteratively and actively acquire extrinsic information, then reason based on acquired historical knowledge. Specifically, during each step of the solving process, the model selects an action to execute, such as querying external knowledge or performing a single logical reasoning step, to gradually progress toward a final answer. Our method can effectively leverage plug-and-play external knowledge and dynamically adjust the strategy for solving complex questions. Evaluated on the StrategyQA dataset, our method achieves 78.17% accuracy with less than 6% parameters of its competitors, setting new SOTA in the ~10B LLM class.

Typical generative dialogue models utilize the dialogue history to generate the response. However, since one dialogue utterance can often be appropriately answered by multiple distinct responses, generating a desired response solely based on the historical information is not easy. Intuitively, if the chatbot can foresee in advance what the user would talk about (i.e., the dialogue future) after receiving its response, it could possibly provide a more informative response. Accordingly, we propose a novel dialogue generation framework named ProphetChat that utilizes the simulated dialogue futures in the inference phase to enhance response generation. To enable the chatbot to foresee the dialogue future, we design a beam-search-like roll-out strategy for dialogue future simulation using a typical dialogue generation model and a dialogue selector. With the simulated futures, we then utilize the ensemble of a history-to-response generator and a future-to-response generator to jointly generate a more informative response. Experiments on two popular open-domain dialogue datasets demonstrate that ProphetChat can generate better responses over strong baselines, which validates the advantages of incorporating the simulated dialogue futures.

Transferring the knowledge to a small model through distillation has raised great interest in recent years. Prevailing methods transfer the knowledge derived from mono-granularity language units (e.g., token-level or sample-level), which is not enough to represent the rich semantics of a text and may lose some vital knowledge. Besides, these methods form the knowledge as individual representations or their simple dependencies, neglecting abundant structural relations among intermediate representations. To overcome the problems, we present a novel knowledge distillation framework that gathers intermediate representations from multiple semantic granularities (e.g., tokens, spans and samples) and forms the knowledge as more sophisticated structural relations specified as the pair-wise interactions and the triplet-wise geometric angles based on multi-granularity representations. Moreover, we propose distilling the well-organized multi-granularity structural knowledge to the student hierarchically across layers. Experimental results on GLUE benchmark demonstrate that our method outperforms advanced distillation methods.

Grounding dialogue agents with knowledge documents has sparked increased attention in both academia and industry. Recently, a growing body of work is trying to build retrieval-based knowledge-grounded dialogue systems. While promising, these approaches require collecting pairs of dialogue context and the corresponding ground-truth knowledge sentences that contain the information regarding the dialogue context. Unfortunately, hand-labeling data to that end is time-consuming, and many datasets and applications lack such knowledge annotations. In this paper, we propose a reciprocal learning approach to jointly optimize a knowledge retriever and a response ranker for knowledge-grounded response retrieval without ground-truth knowledge labels. Specifically, the knowledge retriever uses the feedback from the response ranker as pseudo supervised signals of knowledge retrieval for updating its parameters, while the response ranker also receives the top-ranked knowledge sentences from knowledge retriever for optimization. Evaluation results on two public benchmarks show that our model can significantly outperform previous state-of-the-art methods.

Knowledge distillation has been proven effective when customizing small language models for specific tasks. Here, a corpus as ‘textbook’ plays an indispensable role, only through which the teacher can teach the student. Prevailing methods adopt a two-stage distillation paradigm: general distillation first with task-agnostic general corpus and task-specific distillation next with augmented task-specific corpus. We argue that such a paradigm may not be optimal. In general distillation, it’s extravagant to let the diverse but desultory general knowledge overwhelms the limited model capacity of the student. While in task-specific distillation, the task corpus is usually limited and narrow, preventing the student from learning enough knowledge. To mitigate the issues in the two gapped corpora, we present a better textbook for the student to learn: contextualized corpus that contextualizes task corpus with large-scale general corpus through relevance-based text retrieval. Experimental results on GLUE benchmark demonstrate that contextualized corpus is the better textbook compared with jointly using general corpus and augmented task-specific corpus. Surprisingly, it enables task-specific distillation from scratch without general distillation while maintaining comparable performance, making it more flexible to customize the student model with desired model size under various computation constraints.

Large-scale language models coupled with prompts have shown remarkable performance on few-shot learning. However, through systematic experiments, we find that the few-shot performance of small language models is poor, and using prompts on them brings fewer improvements than on larger ones. In this paper, we propose SMASH, an approach to improve SMAll language models’ few-SHot ability by training on intermediate tasks before prompt-based fine-tuning on downstream tasks. We design intermediate tasks for sentence-pair tasks and sentiment classification tasks by creating training examples with prompt templates similar to downstream tasks using sentences sampled from a large-scale unsupervised corpus, and apply knowledge distillation to distill from outputs of larger pre-trained models as the training objective. We conduct extensive experiments and show that SMASH can make a 6-layer DistilRoBRETa-base achieve comparable performance on few-shot datasets with a 12-layer RoBERTa-base at a low cost.

Building retrieval-based dialogue models that can predict appropriate responses based on the understanding of multi-turn context messages is a challenging problem. Early models usually concatenate all utterances or independently encode each dialogue turn, which may lead to an inadequate understanding of dialogue status. Although a few researchers have noticed the importance of context modeling in multi-turn response prediction, there is no systematic comparison to analyze how to model context effectively and no framework to unify those methods. In this paper, instead of configuring new architectures, we investigate how to improve existing models with a better context modeling method. Specifically, we heuristically summarize three categories of turn-aware context modeling strategies which model the context messages from the perspective of sequential relationship, local relationship, and query-aware manner respectively. A Turn-Aware Context Modeling (TACM) layer is explored to flexibly adapt and unify these context modeling strategies to several advanced response selection models. Evaluation results on three public data sets indicate that employing each individual context modeling strategy or multiple strategies can consistently improve the performance of existing models.

随着人工智能的发展,越来越多的研究开始关注人工智能伦理。在NLP领域,道德自动识别作为研究分析文本中的道德的一项重要任务,近年来开始受到研究者的关注。该任务旨在识别文本中的道德片段,其对自然语言处理的道德相关的下游任务如偏见识别消除、判定模型隐形歧视等具有重要意义。与英文相比,目前面向中文的道德识别研究开展缓慢,其主要原因是至今还没有较大型的道德中文数据集为研究提供数据。为解决上述问题,本文在中文语料上进行了中文道德句的标注工作,并初步对识别中文文本道德句进行探索。我们首先构建了国内首个10万级别的中文道德句数据集,然后本文提出了利用流行的几种机器学习方法探究识别中文道德句任务的效果。此外,我们还探索了利用额外知识辅助的方法,对中文道德句的识别任务进行了进一步的探究。

汉越平行句对抽取是缓解汉越平行语料库数据稀缺的重要方法。平行句对抽取可转换为同一语义空间下的句子相似性分类任务,其核心在于双语语义空间对齐。传统语义空间对齐方法依赖于大规模的双语平行语料,越南语作为低资源语言获取大规模平行语料相对困难。针对这个问题本文提出一种利用种子词典进行跨语言双语预训练及Bi-LSTM(Bi-directional Long Short-Term Memory)的汉-越平行句对抽取方法。预训练中仅需要大量的汉越单语和一个汉越种子词典,通过利用汉越种子词典将汉越双语映射到公共语义空间进行词对齐。再利用Bi-LSTM和CNN(Convolutional Neural Networks)分别提取句子的全局特征和局部特征从而最大化表示汉-越句对之间的语义相关性。实验结果表明,本文模型在F1得分上提升7.1%,优于基线模型。

道德词典资源的建设是人工智能伦理计算的一个研究重点。由于道德行为复杂多样,现有的英文道德词典分类体系并不完善,而中文方面目前尚未有相关的词典资源,理论体系和构建方法仍待探究。针对以上问题,该文提出了面向人工智能伦理计算的中文道德词典构建任务,设计了四类标签和四种类型,得到包含25,012个词的中文道德词典资源。实验结果表明,该词典资源不仅能够使机器学会道德知识,判断词的道德标签和类型,而且能够为句子级别的道德文本分析提供数据支持。

Counterfactuals describe events counter to facts and hence naturally involve common sense, knowledge, and reasoning. SemEval 2020 task 5 is focusing on this field. We participate in the subtask 1 and we use BERT as our system. Our Innovations are feature extraction and data augmentation. We extract and summarize features of counterfactual statements, augment counterfactual examples in training set with the help of these features, and two general methods of data augmentation is experimented in our work. We demonstrate the effectiveness of our approaches, which achieves 0.95 of subtask 1 in F1 while using only a subset of giving training set to fine-tune the BERT model, and our official submission achieves F1 0.802, which ranks us 16th in the competition.

This paper describes the Kingsoft AI Lab’s submission to the WMT2019 news translation shared task. We participated in two language directions: English-Chinese and Chinese-English. For both language directions, we trained several variants of Transformer models using the provided parallel data enlarged with a large quantity of back-translated monolingual data. The best translation result was obtained with ensemble and reranking techniques. According to automatic metrics (BLEU) our Chinese-English system reached the second highest score, and our English-Chinese system reached the second highest score for this subtask.

We describe the system developed by the team of the National University of Singapore for the Chinese-English BTEC task of the IWSLT 2009 evaluation campaign. We adopted a state-of-the-art phrase-based statistical machine translation approach and focused on experiments with different Chinese word segmentation standards. In our official submission, we trained a separate system for each segmenter and we combined the outputs in a subsequent re-ranking step. Given the small size of the training data, we further re-trained the system on the development data after tuning. The evaluation results show that both strategies yield sizeable and consistent improvements in translation quality.