论文检索

Luan Thanh Nguyen

Recent advancements in hate speech detection (HSD) in Vietnamese have made significant progress, primarily attributed to the emergence of transformer-based pre-trained language models, particularly those built on the BERT architecture. However, the necessity for specialized fine-tuned models has resulted in the complexity and fragmentation of developing a multitasking HSD system. Moreover, most current methodologies focus on fine-tuning general pre-trained models, primarily trained on formal textual datasets like Wikipedia, which may not accurately capture human behavior on online platforms. In this research, we introduce ViHateT5, a T5-based model pre-trained on our proposed large-scale domain-specific dataset named VOZ-HSD. By harnessing the power of a text-to-text architecture, ViHateT5 can tackle multiple tasks using a unified model and achieve state-of-the-art performance across all standard HSD benchmarks in Vietnamese. Our experiments also underscore the significance of label distribution in pre-training data on model efficacy. We provide our experimental materials for research purposes, including the VOZ-HSD dataset, pre-trained checkpoint, the unified HSD-multitask ViHateT5 model, and related source code on GitHub publicly.

Nathanaël Beau, Benoit Crabbé

We introduce a novel dataset tailored for code generation, aimed at aiding developers in common tasks. Our dataset provides examples that include a clarified intent, code snippets associated, and an average of three related unit tests. It encompasses a range of libraries such as Pandas, Numpy, and Regex, along with more than 70 standard libraries in Python code derived from Stack Overflow. Comprising 3,402 crafted examples by Python experts, our dataset is designed for both model finetuning and standalone evaluation. To complete unit tests evaluation, we categorize examples in order to get more fine grained analysis, enhancing the understanding of models’ strengths and weaknesses in specific coding tasks. The examples have been refined to reduce data contamination, a process confirmed by the performance of three leading models: Mistral 7B, CodeLLAMA 13B, and Starcoder 15B. We further investigate data-contamination testing GPT-4 performance on a part of our dataset. The benchmark can be accessed at anonymized address.

Qiming Bao, Alex Yuxuan Peng, Zhenyun Deng, Wanjun Zhong, Gaël Gendron, Timothy Pistotti, Neşet Tan, Nathan Young, Yang Chen, Yonghua Zhu 等

Combining large language models with logical reasoning enhances their capacity to address problems in a robust and reliable manner. Nevertheless, the intricate nature of logical reasoning poses challenges when gathering reliable data from the web to build comprehensive training datasets, subsequently affecting performance on downstream tasks. To address this, we introduce a novel logic-driven data augmentation approach, AMR-LDA. AMR-LDA converts the original text into an Abstract Meaning Representation (AMR) graph, a structured semantic representation that encapsulates the logical structure of the sentence, upon which operations are performed to generate logically modified AMR graphs. The modified AMR graphs are subsequently converted back into text to create augmented data. Notably, our methodology is architecture-agnostic and enhances both generative large language models, such as GPT-3.5 and GPT-4, through prompt augmentation, and discriminative large language models through contrastive learning with logic-driven data augmentation. Empirical evidence underscores the efficacy of our proposed method with improvement in performance across seven downstream tasks, such as reading comprehension requiring logical reasoning, textual entailment, and natural language inference. Furthermore, our method leads on the ReClor leaderboard at https://eval.ai/web/challenges/challenge-page/503/leaderboard/1347. The source code and data are publicly available at https://github.com/Strong-AI-Lab/Logical-Equivalence-driven-AMR-Data-Augmentation-for-Representation-Learning.

Govind Krishnan Gangadhar, Karl Stratos

Standard fine-tuning is considered not as effective as specialized methods for model editing due to its comparatively poor performance. However, it is simple, agnostic to the architectural details of the model being edited, and able to leverage advances in standard training techniques with no additional work (e.g., black-box PEFT for computational efficiency), making it an appealing choice for a model editor. In this work, we show that standard fine-tuning alone can yield competitive model editing performance with two minor modifications. First, we optimize the conditional likelihood rather than the full likelihood. Second, in addition to the typical practice of training on randomly paraphrased edit prompts to encourage generalization, we also train on random or similar unedited facts to encourage locality. Our experiments on the ZsRE and CounterFact datasets demonstrate that these simple modifications allow standard fine-tuning to match or outperform highly specialized editors in terms of edit score.

Wanhong Huang, Yi Feng, Chuanyi Li, Honghan Wu, Jidong Ge, Vincent Ng

Legal Judgment Prediction (LJP) has attracted significant attention in recent years. However, previous studies have primarily focused on cases involving only a single defendant, skipping multi-defendant cases due to complexity and difficulty. To advance research, we introduce CMDL, a large-scale real-world Chinese Multi-Defendant LJP dataset, which consists of over 393,945 cases with nearly 1.2 million defendants in total. For performance evaluation, we propose case-level evaluation metrics dedicated for the multi-defendant scenario. Experimental results on CMDL show existing SOTA approaches demonstrate weakness when applied to cases involving multiple defendants. We highlight several challenges that require attention and resolution.

Yuan Zhang, Wanhong Huang, Yi Feng, Chuanyi Li, Zhiwei Fei, Jidong Ge, Bin Luo, Vincent Ng

Legal Judgment Prediction (LJP) refers to the task of automatically predicting judgment results (e.g., charges, law articles and term of penalty) given the fact description of cases. While SOTA models have achieved high accuracy and F1 scores on public datasets, existing datasets fail to evaluate specific aspects of these models (e.g., legal fairness, which significantly impact their applications in real scenarios). Inspired by functional testing in software engineering, we introduce LJPCHECK, a suite of functional tests for LJP models, to comprehend LJP models’ behaviors and offer diagnostic insights. We illustrate the utility of LJPCHECK on five SOTA LJP models. Extensive experiments reveal vulnerabilities in these models, prompting an in-depth discussion into the underlying reasons of their shortcomings.

Wenxuan Wang, Zhaopeng Tu, Chang Chen, Youliang Yuan, Jen-tse Huang, Wenxiang Jiao, Michael Lyu

Safety lies at the core of developing and deploying large language models (LLMs). However, previous safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English. In this work, we build the first multilingual safety benchmark for LLMs, XSafety, in response to the global deployment of LLMs in practice. XSafety covers 14 kinds of commonly used safety issues across 10 languages that span several language families. We utilize XSafety to empirically study the multilingual safety for 4 widely-used LLMs, including both close-API and open-source models. Experimental results show that all LLMs produce significantly more unsafe responses for non-English queries than English ones, indicating the necessity of developing safety alignment for non-English languages. In addition, we propose a simple and effective prompting method to improve the multilingual safety of ChatGPT by enhancing cross-lingual generalization of safety alignment. Our prompting method can significantly reduce the ratio of unsafe responses by 42% for non-English queries. We will release all the data and results to facilitate future research on LLMs’ safety.

Yanis Labrak, Adrien Bazoge, Emmanuel Morin, Pierre-Antoine Gourraud, Mickael Rouvier, Richard Dufour

Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. Despite the availability of various open-source LLMs tailored for health contexts, adapting general-purpose LLMs to the medical domain presents significant challenges.In this paper, we introduce BioMistral, an open-source LLM tailored for the biomedical domain, utilizing Mistral as its foundation model and further pre-trained on PubMed Central. We conduct a comprehensive evaluation of BioMistral on a benchmark comprising 10 established medical question-answering (QA) tasks in English. We also explore lightweight models obtained through quantization and model merging approaches. Our results demonstrate BioMistral’s superior performance compared to existing open-source medical models and its competitive edge against proprietary counterparts. Finally, to address the limited availability of data beyond English and to assess the multilingual generalization of medical LLMs, we automatically translated and evaluated this benchmark into 7 other languages. This marks the first large-scale multilingual evaluation of LLMs in the medical domain. Datasets, multilingual evaluation benchmarks, scripts, and all the models obtained during our experiments are freely released.

Daniel Tamayo, Aitor Gonzalez-Agirre, Javier Hernando, Marta Villegas

Recent research has explored methods for updating and modifying factual knowledge in large language models, often focusing on specific multi-layer perceptron blocks. This study expands on this work by examining the effectiveness of existing knowledge editing methods across languages and delving into the role of attention mechanisms in this process. Drawing from the insights gained, we propose Mass-Editing Memory with Attention in Transformers (MEMAT), a method that achieves significant improvements in all metrics while requiring minimal parameter modifications. MEMAT delivers a remarkable 10% increase in magnitude metrics, benefits languages not included in the training data and also demonstrates a high degree of portability. Our code and data are at https://github.com/dtamayo-nlp/MEMAT.

Jun-Hyung Park, Mingyu Lee, Junho Kim, SangKeun Lee

In this paper, we introduce COCONUT to effectively guide the contextualization of structured commonsense knowledge based on largelanguage models. COCONUT employs a contextualized knowledge prompting scheme to gather high-quality contextualization examplesfrom a large language model. These examples are subsequently distilled into small language models to enhance their contextualization capability. Extensive evaluations show that COCONUT considerably improves commonsense reasoning performance across diverse benchmarks, models, and settings, exhibiting its flexibility and universality in generating contextualized commonsense knowledge. Notably,COCONUT consistently outperforms the state-of-the-art technique by an average of 5.8%.

Xun Liang, Hanyu Wang, Shichao Song, Mengting Hu, Xunzhi Wang, Zhiyu Li, Feiyu Xiong, Bo Tang

Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes. In this study, we introduce a pluggable CTG framework for Large Language Models (LLMs) named Dynamic Attribute Graphs-based controlled text generation (DATG). This framework utilizes an attribute scorer to evaluate the attributes of sentences generated by LLMs and constructs dynamic attribute graphs. DATG modulates the occurrence of key attribute words and key anti-attribute words, achieving effective attribute control without compromising the original capabilities of the model. We conduct experiments across four datasets in two tasks: toxicity mitigation and sentiment transformation, employing five LLMs as foundational models. Our findings highlight a remarkable enhancement in control accuracy, achieving a peak improvement of 19.29% over baseline methods in the most favorable task across four datasets. Additionally, we observe a significant decrease in perplexity, markedly improving text fluency.

Haz Shahgir, Xianghao Kong, Greg Ver Steeg, Yue Dong

The widespread use of Text-to-Image (T2I) models in content generation requires careful examination of their safety, including their robustness to adversarial attacks. Despite extensive research on adversarial attacks, the reasons for their effectiveness remain underexplored. This paper presents an empirical study on adversarial attacks against T2I models, focusing on analyzing factors associated with attack success rates (ASR). We introduce a new attack objective - entity swapping using adversarial suffixes and two gradient-based attack algorithms. Human and automatic evaluations reveal the asymmetric nature of ASRs on entity swap: for example, it is easier to replace “human” with “robot” in the prompt “a human dancing in the rain.” with an adversarial suffix, but the reverse replacement is significantly harder. We further propose probing metrics to establish indicative signals from the model’s beliefs to the adversarial ASR. We identify conditions that result in a success probability of 60% for adversarial attacks and others where this likelihood drops below 5%. The code and data are available at https://github.com/Patchwork53/AsymmetricAttack

Yuxiang Cai, Qiao Liu, Yanglei Gan, Changlin Li, Xueyi Liu, Run Lin, Da Luo, JiayeYang JiayeYang

Temporal Knowledge Graph (TKG) reasoning seeks to predict future incomplete facts leveraging historical data. While existing approaches have shown effectiveness in addressing the task through various perspectives, such as graph learning and logic rules, they are limited in capturing the indeterminacy in future events, particularly in the case of rare/unseen facts. To tackle the highlighted issues, we introduce a novel approach by conceptualizing TKG reasoning as a sequence denoising process for future facts, namely DiffuTKG. Concretely, we first encodes the historical events as the conditional sequence. Then we gradually introduce Gaussian noise to corrupt target facts during the forward process and then employ a transformer-based conditional denoiser to restore them in the reverse phase. Moreover, we introduce an uncertainty regularization loss to mitigate the risk of prediction biases by favoring frequent scenarios over rare/unseen facts. Empirical results on four real-world datasets show that DiffuTKG outperforms state-of-the-art methods across multiple evaluation metrics.

Xinlin Zhuang, Hongyi Wu, Xinshu Shen, Peimin Yu, Gaowei Yi, Xinhao Chen, Tu Hu, Yang Chen, Yupei Ren, Yadong Zhang 等

Topic relevance of an essay demands that the composition adheres to a clear theme and aligns well with the essay prompt requirements, a critical aspect of essay quality evaluation. However, existing research of Automatic Essay Scoring (AES) for Chinese essays has overlooked topic relevance and lacks detailed feedback, while Automatic Essay Comment Generation (AECG) faces much complexity and difficulty. Additionally, current Large Language Models, including GPT-4, often make incorrect judgments and provide overly impractical feedback when evaluating topic relevance. This paper introduces TOREE (Topic Relevance Evaluation), a comprehensive dataset developed to assess topic relevance in Chinese primary and middle school students’ essays, which is beneficial for AES, AECG and other applications. Moreover, our proposed two-step method utilizes TOREE through a combination of Supervised Fine-tuning and Preference Learning. Experimental results demonstrate that TOREE is of high quality, and our method significantly enhances models’ performance on two designed tasks for topic relevance evaluation, improving both automatic and human evaluations across four diverse LLMs.

Wei Pang, Chuan Zhou, Xiao-Hua Zhou, Xiaojie Wang

Instruction Fine-Tuning, a method enhancing pre-trained language models’ capabilities from mere next-word prediction to complex instruction following, often employs a one-off training approach on diverse instruction dataset. However, this method may not effectively enhance models’ adherence to instructions due to the simultaneous handling of varying instruction complexities. To address this, we propose a novel phased instruction fine-tuning (Phased IFT) method, grounded in the hypothesis of progressive alignment, which posits that the transition of a pre-trained language model from simple next-word prediction to sophisticated instruction following is a gradual learning process. Specifically, we obtain the score of difficulty for each instruction via GPT-4, stratify the instruction data into subsets of increasing difficulty, and sequentially uptrain on these subsets using the standard supervised loss. Through extensive experiments on the pre-trained models Llama-2 7B/13B, and Mistral-7B using the 52K Alpaca instruction data, we demonstrate that Phased IFT significantly surpasses traditional one-off instruction fine-tuning (One-off IFT) method in win rate, empirically validating the progressive alignment hypothesis. Our findings suggest that Phased IFT offers a simple yet effective pathway for elevating the instruction-following capabilities of pre-trained language models.

Marta R. Costa-jussà, Mariano Coria Meglioli, Pierre Andrews, David Dale, Prangthip Hansanti, Elahe Kalbassi, Alex Mourachko, Christophe Ropers, Carleigh Wood

Research in toxicity detection in natural language processing for the speech modality (audio-based) is quite limited, particularly for languages other than English. To address these limitations and lay the groundwork for truly multilingual audio-based toxicity detection, we introduce MuTox, the first highly multilingual audio-based dataset with toxicity labels which covers 14 different linguistic families. The dataset comprises 20,000 audio utterances for English and Spanish, and 4,000 for the other 28 languages. To demonstrate the quality of this dataset, we trained the MuTox audio-based toxicity classifier, which enables zero-shot toxicity detection across a wide range of languages. This classifier performs on par with existing text-based trainable classifiers, while expanding the language coverage more than tenfold. When compared to a wordlist-based classifier that covers a similar number of languages, MuTox improves F1-Score by an average of 100%. This significant improvement underscores the potential of MuTox in advancing the field of audio-based toxicity detection.

Mariia Fedorova, Andrey Kutuzov, Yves Scherrer

We use contextualized word definitions generated by large language models as semantic representations in the task of diachronic lexical semantic change detection (LSCD). In short, generated definitions are used as ‘senses’, and the change score of a target word is retrieved by comparing their distributions in two time periods under comparison. On the material of five datasets and three languages, we show that generated definitions are indeed specific and general enough to convey a signal sufficient to rank sets of words by the degree of their semantic change over time. Our approach is on par with or outperforms prior non-supervised sense-based LSCD methods. At the same time, it preserves interpretability and allows to inspect the reasons behind a specific shift in terms of discrete definitions-as-senses. This is another step in the direction of explainable semantic change modeling.

Zhipeng Chen, Kun Zhou, Wayne Xin Zhao, Junchen Wan, Fuzheng Zhang, Di Zhang, Ji-Rong Wen

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, e.g., reducing harmfulness and errors. However, existing RL methods mainly adopt instance-level reward, which cannot provide fine-grained supervision for complex reasoning tasks. As a result, the RL training cannot be fully aware of the specific part or step that actually leads to the incorrectness in model response. To address it, we propose a new RL method named RLMEC that incorporates a generative model as the reward model, which is trained by the erroneous solution rewriting task under the minimum editing constraint, which can produce token-level supervision for RL training. Based 0on the generative reward model, we design the token-level RL objective for training and an imitation-based regularization for stabilizing RL process. And these two objectives focus on the revision of the key tokens for the erroneous solution, reducing the effect of other unimportant tokens. Experiment results on 8 tasks have demonstrated the effectiveness of our approach. Our code and data will be publicly released.

Jie Zhu, Junhui Li, Yalong Wen, Lifan Guo

In light of recent breakthroughs in large language models (LLMs) that have revolutionized natural language processing (NLP), there is an urgent need for new benchmarks to keep pace with the fast development of LLMs. In this paper, we propose CFLUE, the Chinese Financial Language Understanding Evaluation benchmark, designed to assess the capability of LLMs across various dimensions. Specifically, CFLUE provides datasets tailored for both knowledge assessment and application assessment. In knowledge assessment, it consists of 38K+ multiple-choice questions with associated solution explanations. These questions serve dual purposes: answer prediction and question reasoning. In application assessment, CFLUE features 16K+ test instances across distinct groups of NLP tasks such as text classification, machine translation, relation extraction, reading comprehension, and text generation. Upon CFLUE, we conduct a thorough evaluation of representative LLMs. The results reveal that only Qwen-72B, GPT-4, and GPT-4-turbo achieve an accuracy exceeding 60% in answer prediction for knowledge assessment, suggesting that there is still substantial room for improvement in current LLMs. In application assessment, while GPT-4 and GPT-4-turbo rank as the top two performers on average, their significant advantage over open-source LLMs is noticeably diminished, given that Qwen-72B achieves the best performance in 2 out of 5 tasks. The datasets and scripts associated with CFLUE are openly accessible at https://github.com/aliyun/cflue.

Yanjiang Liu, Tianyun Zhong, Yaojie Lu, Hongyu Lin, Ben He, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han 等

The eXtreme Multi-label Classification (XMC) aims at accurately assigning large-scale labels to instances, and is challenging for learning, managing, and predicting over the large-scale and rapidly growing set of labels. Traditional XMC methods, like one-vs-all and tree-based methods struggle with the growing set of labels due to their static label assumptions, and embedding-based methods struggle with the complex mapping relationships due to their late-interaction paradigm. In this paper, we propose a large language model (LLM) powered agent framework for extreme multi-label classification – XMC-Agent, which can effectively learn, manage and predict the extremely large and dynamically increasing set of labels. Specifically, XMC-Agent models the extreme multi-label classification task as a dynamic navigation problem, employing a scalable hierarchical label index to effectively manage the unified label space. Additionally, we propose two algorithms to enhance the dynamic navigation capabilities of XMC-Agent: a self-construction algorithm for building the scalable hierarchical index, and an iterative feedback learning algorithm for adjusting the agent to specific tasks. Experiments show that XMC-Agentachieves the state-of-the-art performance on three standard datasets.