Existing paper review methods often rely on superficial manuscript features or directly on large language models (LLMs), which are prone to hallucinations, biased scoring, and limited reasoning capabilities. Moreover, these methods often fail to capture the complex argumentative reasoning and negotiation dynamics inherent in reviewer-author interactions. To address these limitations, we propose ReViewGraph (Reviewer-Author Debates Graph Reasoner), a novel framework that performs heterogeneous graph reasoning over LLM-simulated multi-round reviewer-author debates. In our approach, reviewer-author exchanges are simulated through LLM-based multi-agent collaboration. Diverse opinion relations (e.g., acceptance, rejection, clarification, and compromise) are then explicitly extracted and encoded as typed edges within a heterogeneous interaction graph. By applying graph neural networks to reason over these structured debate graphs, ReViewGraph captures fine-grained argumentative dynamics and enables more informed review decisions. Extensive experiments on three datasets demonstrate that ReViewGraph outperforms strong baselines with an average relative improvement of 15.73%, underscoring the value of modeling detailed reviewer–author debate structures.

Text-to-visualization (text-to-vis) models for tabular data have become essential tools in the era of big data, enabling users to generate visualizations and make data-driven decisions through natural language queries (NLQs). Despite their growing adoption, the security vulnerabilities of these models remain largely unexplored. To address this gap, we propose VisPoison, a backdoor attack framework that realistically simulates three types of attacks on text-to-vis models via data poisoning: data exposure, misleading visualizations, and denial-of-service (DoS). Specifically, VisPoison introduces two types of stealthy triggers to enable both proactive and passive backdoor activations. Proactive triggers are deliberately inserted by attackers using rare-word patterns to extract sensitive information, whereas passive triggers are unintentionally activated by users through first-word prompts, resulting in visualization errors or DoS failures. To support these triggers, we craft specialized payloads for visualization queries that allow compromised models to function normally on benign inputs while producing malicious outputs in the presence of triggers. Extensive evaluations on both trainable and in-context learning (ICL)-based text-to-vis models show that VisPoison achieves attack success rates exceeding 90\%, exposing serious vulnerabilities. Additionally, existing defense strategies reveal limited effectiveness against VisPoison, underscoring the urgent need for more robust and security-aware text-to-vis systems to safeguard human-data interaction.

The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests to become unreliable. If any model has been trained on a benchmark test set, it can seriously hinder the health of the field. In order to automate and efficiently test the capabilities of large language models, numerous mainstream benchmarks adopt a multiple-choice format. As the swapping of the contents of multiple-choice options does not affect the meaning of the question itself, we propose a simple and effective data leakage detection method based on this property. Specifically, we shuffle the contents of the options in the data to generate the corresponding derived data sets, and then detect data leakage based on the model's log probability distribution over the derived data sets. If there is a maximum and outlier in the set of log probabilities, it indicates that the data is leaked. Our method is able to work under gray-box conditions without access to model training data or weights, effectively identifying data leakage from benchmark test sets in model pre-training data, including both normal scenarios and complex scenarios where options may have been shuffled intentionally or unintentionally. Through experiments based on two LLMs and benchmark designs, we demonstrate the effectiveness of our method. In addition, we evaluate the degree of data leakage of 35 mainstream open-source LLMs on four benchmark datasets and give a ranking of the leaked LLMs for each benchmark, and we find that the Qwen family of LLMs has the highest degree of data leakage.

As the capabilities of Multimodal Large Language Models (MLLMs) improve, the need for higher-order evaluation of them is increasing. However, there is a lack of work evaluating MLLM for higher-order perception and understanding of Chinese visual content. To address this, we introduce the CII-Bench, which aims to assess MLLMs’ such capabilities for Chinese images. To ensure the authenticity of the Chinese context, images in CII-Bench are sourced from the Chinese Internet and manually reviewed, with corresponding answers also manually crafted. Additionally, CII-Bench incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, which can deeply reflect the model’s understanding of Chinese traditional culture. Through experiments on multiple MLLMs using CII-Bench, significant findings emerged. There is a large gap between MLLMs and humans in performance. The highest MLLM accuracy is 64.4%, while the human average is 78.2% and the peak is 81.0%. MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture. Moreover, most models have higher accuracy when image emotion hints are added to the prompts. We believe CII-Bench will help MLLMs better understand Chinese semantics and specific images, and move forward the development of expert artificial general intelligence (AGI). Our project is publicly available at https://cii-bench.github.io.

Sunbowen Lee, Junting Zhou, Chang Ao, Kaige Li, Xeron Du, Sirui He, Haihong Wu, Tianci Liu, Jiaheng Liu, Hamid Alinejad-Rokny, Min Yang, Yitao Liang, Zhoufutu Wen, Shiwen Ni. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Dingwei Chen, Ziqiang Liu, Feiteng Fang, Chak Tou Leong, Shiwen Ni, Ahmadreza Argha, Hamid Alinejad-Rokny, Min Yang, Chengming Li. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Legal question answering (QA) has attracted increasing attention from people seeking legal advice, which aims to retrieve the most applicable answers from a large-scale database of question-answer pairs. Previous methods mainly use a dual-encoder architecture to learn dense representations of both questions and answers. However, these methods could suffer from lacking domain knowledge and sufficient labeled training data. In this paper, we propose a three-stage (pre-training, fine-tuning and re-ranking) framework for legal QA (called PFR-LQA), which promotes the fine-grained text representation learning and boosts the performance of dense retrieval with the dual-encoder architecture. Concretely, we first conduct domain-specific pre-training on legal questions and answers through a self-supervised training objective, allowing the pre-trained model to be adapted to the legal domain. Then, we perform task-specific fine-tuning of the dual-encoder on legal question-answer pairs by using the supervised learning objective, leading to a high-quality dual-encoder for the specific downstream QA task. Finally, we employ a contextual re-ranking objective to further refine the output representations of questions produced by the document encoder, which uses contextual similarity to increase the discrepancy between the anchor and hard negative samples for better question re-ranking. We conduct extensive experiments on a manually annotated legal QA dataset. Experimental results show that our PFR-LQA method achieves better performance than the strong competitors for legal question answering.

Large Language Models (LLMs) have shown remarkable capabilities, yet ensuring their outputs conform to strict structural or grammatical constraints remains challenging, which is critical in function calls and domain-specific language (DSL) generation. Constrained decoding with context-free grammar is a flexible approach to guarantee LLMs’ adherence to a specific format by dynamically building a token logits mask. However, creating this mask requires checking the validity of all tokens in the LLM vocabulary at every decoding step, which often incurs significant overheads in existing constrained decoding engines. To address this challenge, we propose $\textbf{ZapFormat}$, a novel $\textbf{dynamic pruning}$ strategy based on the Earley algorithm that identifies and eliminates invalid or redundant Earley states in real-time, significantly reducing memory occupation of the Earley algorithm’s states. This further enables us to use a state cache to speed up structured generations on a large number of queries. We implemented ZapFormat in a new constrained decoding engine called Formatron which also incorporates existing optimizations. Through comprehensive experiments on structured generation tasks, including JSON generation, JSON Schema validation, and semantic parsing, we demonstrate that Formatron not only $\textbf{consistently maintains}$ high-precision compliant outputs but also achieves $\textbf{significant improvements}$ in inference speed up to 2x compared to state-of-the-art implementations. More importantly, Formatron is generally applicable across various LLM architectures. We release Formatron as open source at https://github.com/Dan-wanna-M/formatron.

Large Language Models (LLMs) exhibit substantial capabilities yet encounter challenges, including hallucination, outdated knowledge, and untraceable reasoning processes.Retrievalaugmented generation (RAG) has emerged as a promising solution, integrating knowledge from external databases to mitigate these challenges.However, inappropriate retrieved passages can potentially hinder the LLMs' capacity to generate comprehensive and high-quality responses.Prior RAG studies on the robustness of retrieval noises often confine themselves to a limited set of noise types, deviating from realworld retrieval environments and limiting practical applicability.In this study, we initially investigate retrieval noises and categorize them into three distinct types, reflecting real-world environments.We analyze the impact of these various retrieval noises on the robustness of LLMs.Subsequently, we propose a novel RAG approach known as Retrieval-augmented Adaptive Adversarial Training (RAAT).RAAT leverages adaptive adversarial training to dynamically adjust the model's training process in response to retrieval noises.Concurrently, it employs multi-task learning to ensure the model's capacity to internally recognize noisy contexts.Extensive experiments demonstrate that the LLaMA-2 7B model trained using RAAT exhibits significant improvements in F1 and EM scores under diverse noise conditions.For reproducibility, we release our code and data at: https://github.com/calubkk/RAAT.

Recent advancements in Large Language Models (LLMs) have showcased their remarkable capabilities in text understanding and generation.However, even stronger LLMs are susceptible to acquiring erroneous or obsolete information from the training corpus.Direct secondary fine-tuning with data containing new knowledge may be ineffective in updating knowledge due to the conflict between old and new knowledge.In this paper, we propose a new paradigm for fine-tuning called F-Learning (Forgetting before Learning), which employs parametric arithmetic to facilitate the forgetting of old knowledge and learning of new knowledge.Experimental results on two publicly available datasets demonstrate that our proposed F-Learning can obviously improve the knowledge updating performance of both full fine-tuning and LoRA fine-tuning, simultaneously outperforming the existing baselines in most cases.Moreover, we have also discovered that forgetting old knowledge by subtracting the parameters of LoRA can yield a similar effect to subtracting the parameters of full fine-tuning, and occasionally even surpass it significantly.

Traditional legal retrieval systems designed to retrieve legal documents, statutes, precedents, and other legal information are unable to give satisfactory answers due to lack of semantic understanding of specific questions. Large Language Models (LLMs) have achieved excellent results in a variety of natural language processing tasks, which inspired us that we train a LLM in the legal domain to help legal retrieval. However, in the Chinese legal domain, due to the complexity of legal questions and the rigour of legal articles, there is no legal large model with satisfactory practical application yet. In this paper, we present DeliLaw, a Chinese legal counselling system based on a large language model. DeliLaw integrates a legal retrieval module and a case retrieval module to overcome the model hallucination. Users can consult professional legal questions, search for legal articles and relevant judgement cases, etc. on the DeliLaw system in a dialogue mode. In addition, DeliLaw supports the use of English for counseling. we provide the address of the system: https://data.delilegal.com/lawQuestion.

Large language models (LLMs) have demonstrated impressive performance in various natural language processing (NLP) tasks. However, there is limited understanding of how well LLMs perform in specific domains (e.g, the intellectual property (IP) domain). In this paper, we contribute a new benchmark, the first Multilingual-oriented quiZ on Intellectual Property (MoZIP), for the evaluation of LLMs in the IP domain. The MoZIP benchmark includes three challenging tasks: IP multiple-choice quiz (IPQuiz), IP question answering (IPQA), and patent matching (PatentMatch). In addition, we also develop a new IP-oriented multilingual large language model (called MoZi), which is a BLOOMZ-based model that has been supervised fine-tuned with multilingual IP-related text data. We evaluate our proposed MoZi model and four well-known LLMs (i.e., BLOOMZ, BELLE, ChatGLM and ChatGPT) on the MoZIP benchmark. Experimental results demonstrate that MoZi outperforms BLOOMZ, BELLE and ChatGLM by a noticeable margin, while it had lower scores compared with ChatGPT. Notably, the performance of current LLMs on the MoZIP benchmark has much room for improvement, and even the most powerful ChatGPT does not reach the passing level. Our source code, data, and models are available at https://github.com/AI-for-Science/MoZi.

Among the various pre-trained neural language models that are popular today, dropout is already an indispensable regularization technique. To solve the inconsistency between training and inference caused by the randomness of dropout, some studies use consistency training to regularize dropout at the output layer. In this paper, we propose a novel Layer-wise Regularized Dropout (LR-Drop), which is specially designed for Transformer-based Language models. Specifically, LR-Drop layer-wise regularizes each Transformer layer using the consistency training strategy. Each training sample passes through the two siamese sub-models sampled by dropout, and then LR-Drop forces the hidden states, multi-head attention matrices, and output distribution of the two siamese sub-models to be consistent. The proposed LR-Drop can be regarded as a “self-distillation” framework, in which each sub-model generated by dropout is the other’s “teacher” model and “student” model. Through extensive experiments on 8 natural language understanding datasets, 6 neural machine translation datasets, and 1 abstractive summarization dataset (a total of 15 datasets), we show that LR-Drop achieves superior performances, including state-of-the-art results.

The rapid advancements in the development of multimodal large language models (MLLMs) have consistently led to new breakthroughs on various benchmarks. In response, numerous challenging and comprehensive benchmarks have been proposed to more accurately assess the capabilities of MLLMs. However, there is a dearth of exploration of the higher-order perceptual capabilities of MLLMs. To fill this gap, we propose the Image Implication understanding Benchmark, II-Bench, which aims to evaluate the model's higher-order perception of images. Through extensive experiments on II-Bench across multiple MLLMs, we have made significant findings. Initially, a substantial gap is observed between the performance of MLLMs and humans on II-Bench. The pinnacle accuracy of MLLMs attains 74.8%, whereas human accuracy averages 90%, peaking at an impressive 98%. Subsequently, MLLMs perform worse on abstract and complex images, suggesting limitations in their ability to understand high-level semantics and capture image details. Finally, it is observed that most models exhibit enhanced accuracy when image sentiment polarity hints are incorporated into the prompts. This observation underscores a notable deficiency in their inherent understanding of image sentiment. We believe that II-Bench will inspire the community to develop the next generation of MLLMs, advancing the journey towards expert artificial general intelligence (AGI). II-Bench is publicly available at https://huggingface.co/datasets/m-a-p/II-Bench.

Adversarial training has been proven to be a powerful regularization technique to improve language models. In this work, we propose a novel randomdropped weightattackadversarial training method (DropAttack) for natural language understanding. Our DropAttack improves the generalization of models by minimizing the internal adversarial risk caused by a multitude of attack combinations. Specifically, DropAttack enhances the adversarial attack space by intentionally adding worst-case adversarial perturbations to the weight parameters and randomly dropping the specific proportion of attack perturbations. To extensively validate the effectiveness of DropAttack,12public English natural language understanding datasets were used. Experiments on the GLUE benchmark show that when DropAttack is applied only to the finetuning stage, it is able to improve the overall test scores of the BERT-base pre-trained model from 78.3 to 79.7 and RoBERTa-large pre-trained model from 88.1 to 88.8. Further, DropAttack also significantly improves models trained from scratch. Theoretical analysis reveals that DropAttack performs potential gradient regularization on the input and weight parameters of the model. Moreover, visualization experiments show that DropAttack can push the minimum risk of the neural network to a lower and flatter loss landscape.

In recent years, most of the research on deep learning is based on deep neural networks, which uses the backpropagation algorithm to train parameters of nonlinear layers. Recently, a non-NN style deep model called Deep Forest or gcForest was proposed by Zhou and Feng, which is a deep learning model based on random forests and the training process does not rely on backpropagation. In this paper, we propose PSForest, which can be regarded as a modification of the standard Deep Forest. The main idea for improving the efficiency and performance of the Deep Forest is to do multi-grained pooling of raw features and screening the class vector of each layer based on out-of-bag error. The experiment on different datasets shows that our proposed model achieves predictive accuracy comparable to or better than gcForest, with lower memory requirement and smaller time cost. The study significantly improves the competitiveness of deep forests, further demonstrating that deep learning is more than just deep neural networks.