Xuezhi Cao

Jiawei Chen, Junkang Wu, Jiancan Wu et al.

Recent years have witnessed the great successes of embedding-based methods in recommender systems. Despite their decent performance, we argue one potential limitation of these methods -- the embedding magnitude has not been explicitly modulated, which may aggravate popularity bias and training instability, hindering the model from making a good recommendation. It motivates us to leverage the embedding normalization in recommendation. By normalizing user/item embeddings to a specific value, we empirically observe impressive performance gains (9\% on average) on four real-world datasets. Although encouraging, we also reveal a serious limitation when applying normalization in recommendation -- the performance is highly sensitive to the choice of the temperature $τ$ which controls the scale of the normalized embeddings. To fully foster the merits of the normalization while circumvent its limitation, this work studied on how to adaptively set the proper $τ$. Towards this end, we first make a comprehensive analyses of $τ$ to fully understand its role on recommendation. We then accordingly develop an adaptive fine-grained strategy Adap-$τ$ for the temperature with satisfying four desirable properties including adaptivity, personalized, efficiency and model-agnostic. Extensive experiments have been conducted to validate the effectiveness of the proposal. The code is available at \url{https://github.com/junkangwu/Adap_tau}.

Peng Ding, Jun Kuang, Dan Ma et al.

Large Language Models (LLMs), such as ChatGPT and GPT-4, are designed to provide useful and safe responses. However, adversarial prompts known as 'jailbreaks' can circumvent safeguards, leading LLMs to generate potentially harmful content. Exploring jailbreak prompts can help to better reveal the weaknesses of LLMs and further steer us to secure them. Unfortunately, existing jailbreak methods either suffer from intricate manual design or require optimization on other white-box models, which compromises either generalization or efficiency. In this paper, we generalize jailbreak prompt attacks into two aspects: (1) Prompt Rewriting and (2) Scenario Nesting. Based on this, we propose ReNeLLM, an automatic framework that leverages LLMs themselves to generate effective jailbreak prompts. Extensive experiments demonstrate that ReNeLLM significantly improves the attack success rate while greatly reducing the time cost compared to existing baselines. Our study also reveals the inadequacy of current defense methods in safeguarding LLMs. Finally, we analyze the failure of LLMs defense from the perspective of prompt execution priority, and propose corresponding defense strategies. We hope that our research can catalyze both the academic community and LLMs developers towards the provision of safer and more regulated LLMs. The code is available at https://github.com/NJUNLP/ReNeLLM.

Renyu Zhu, Chengcheng Han, Yong Qian et al. · stanford

We study the problem of multimodal fusion in this paper. Recent exchanging-based methods have been proposed for vision-vision fusion, which aim to exchange embeddings learned from one modality to the other. However, most of them project inputs of multimodalities into different low-dimensional spaces and cannot be applied to the sequential input data. To solve these issues, in this paper, we propose a novel exchanging-based multimodal fusion model MuSE for text-vision fusion based on Transformer. We first use two encoders to separately map multimodal inputs into different low-dimensional spaces. Then we employ two decoders to regularize the embeddings and pull them into the same space. The two decoders capture the correlations between texts and images with the image captioning task and the text-to-image generation task, respectively. Further, based on the regularized embeddings, we present CrossTransformer, which uses two Transformer encoders with shared parameters as the backbone model to exchange knowledge between multimodalities. Specifically, CrossTransformer first learns the global contextual information of the inputs in the shallow layers. After that, it performs inter-modal exchange by selecting a proportion of tokens in one modality and replacing their embeddings with the average of embeddings in the other modality. We conduct extensive experiments to evaluate the performance of MuSE on the Multimodal Named Entity Recognition task and the Multimodal Sentiment Analysis task. Our results show the superiority of MuSE against other competitors. Our code and data are provided at https://github.com/RecklessRonan/MuSE.

Peng Ding, Jingyu Wu, Jun Kuang et al.

Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on various visual-language understanding and generation tasks. However, MLLMs occasionally generate content inconsistent with the given images, which is known as "hallucination". Prior works primarily center on evaluating hallucination using standard, unperturbed benchmarks, which overlook the prevalent occurrence of perturbed inputs in real-world scenarios-such as image cropping or blurring-that are critical for a comprehensive assessment of MLLMs' hallucination. In this paper, to bridge this gap, we propose Hallu-PI, the first benchmark designed to evaluate Hallucination in MLLMs within Perturbed Inputs. Specifically, Hallu-PI consists of seven perturbed scenarios, containing 1,260 perturbed images from 11 object types. Each image is accompanied by detailed annotations, which include fine-grained hallucination types, such as existence, attribute, and relation. We equip these annotations with a rich set of questions, making Hallu-PI suitable for both discriminative and generative tasks. Extensive experiments on 12 mainstream MLLMs, such as GPT-4V and Gemini-Pro Vision, demonstrate that these models exhibit significant hallucinations on Hallu-PI, which is not observed in unperturbed scenarios. Furthermore, our research reveals a severe bias in MLLMs' ability to handle different types of hallucinations. We also design two baselines specifically for perturbed scenarios, namely Perturbed-Reminder and Perturbed-ICL. We hope that our study will bring researchers' attention to the limitations of MLLMs when dealing with perturbed inputs, and spur further investigations to address this issue. Our code and datasets are publicly available at https://github.com/NJUNLP/Hallu-PI.

Chengcheng Han, Renyu Zhu, Jun Kuang et al.

Meta-learning methods have been widely used in few-shot named entity recognition (NER), especially prototype-based methods. However, the Other(O) class is difficult to be represented by a prototype vector because there are generally a large number of samples in the class that have miscellaneous semantics. To solve the problem, we propose MeTNet, which generates prototype vectors for entity types only but not O-class. We design an improved triplet network to map samples and prototype vectors into a low-dimensional space that is easier to be classified and propose an adaptive margin for each entity type. The margin plays as a radius and controls a region with adaptive size in the low-dimensional space. Based on the regions, we propose a new inference procedure to predict the label of a query instance. We conduct extensive experiments in both in-domain and cross-domain settings to show the superiority of MeTNet over other state-of-the-art methods. In particular, we release a Chinese few-shot NER dataset FEW-COMM extracted from a well-known e-commerce platform. To the best of our knowledge, this is the first Chinese few-shot NER dataset. All the datasets and codes are provided at https://github.com/hccngu/MeTNet.

Wentao Shi, Junkang Wu, Xuezhi Cao et al.

Learning hyperbolic embeddings for knowledge graph (KG) has gained increasing attention due to its superiority in capturing hierarchies. However, some important operations in hyperbolic space still lack good definitions, making existing methods unable to fully leverage the merits of hyperbolic space. Specifically, they suffer from two main limitations: 1) existing Graph Convolutional Network (GCN) methods in hyperbolic space rely on tangent space approximation, which would incur approximation error in representation learning, and 2) due to the lack of inner product operation definition in hyperbolic space, existing methods can only measure the plausibility of facts (links) with hyperbolic distance, which is difficult to capture complex data patterns. In this work, we contribute: 1) a Full Poincaré Multi-relational GCN that achieves graph information propagation in hyperbolic space without requiring any approximation, and 2) a hyperbolic generalization of Euclidean inner product that is beneficial to capture both hierarchical and complex patterns. On this basis, we further develop a \textbf{F}ully and \textbf{F}lexible \textbf{H}yperbolic \textbf{R}epresentation framework (\textbf{FFHR}) that is able to transfer recent Euclidean-based advances to hyperbolic space. We demonstrate it by instantiating FFHR with four representative KGC methods. Extensive experiments on benchmark datasets validate the superiority of our FFHRs over their Euclidean counterparts as well as state-of-the-art hyperbolic embedding methods.

Wei Liu, Yang Bai, Chengcheng Han et al.

Direct Preference Optimization (DPO) is widely utilized in the Reinforcement Learning from Human Feedback (RLHF) phase to align Large Language Models (LLMs) with human preferences, thereby enhancing both their harmlessness and efficacy. However, it has been observed that DPO tends to over-optimize for verbosity, which can detrimentally affect both performance and user experience. In this paper, we conduct an in-depth theoretical analysis of DPO's optimization objective and reveal a strong correlation between its implicit reward and data length. This correlation misguides the optimization direction, resulting in length sensitivity during the DPO training and leading to verbosity. To address this issue, we propose a length-desensitization improvement method for DPO, termed LD-DPO. The proposed method aims to desensitize DPO to data length by decoupling explicit length preference, which is relatively insignificant, from the other implicit preferences, thereby enabling more effective learning of the intrinsic preferences. We utilized two settings (Base and Instruct) of Llama2-13B, Llama3-8B, and Qwen2-7B for experimental validation on various benchmarks including MT-Bench and AlpacaEval 2. The experimental results indicate that LD-DPO consistently outperforms DPO and other baseline methods, achieving more concise responses with a 10-40% reduction in length compared to DPO. We conducted in-depth experimental analyses to demonstrate that LD-DPO can indeed achieve length desensitization and align the model more closely with human-like preferences.

Linyue Pan, Yaoming Zhu, Lin Qiu et al.

Self-improving language agents are typically evaluated in isolation: an agent attempts a task, receives feedback, and iteratively refines its own behavior. Yet agents increasingly operate alongside peers whose strategies and outcomes are publicly visible. This raises an under-studied question: when does shared experience produce improvements that self-improvement alone cannot achieve? We introduce SAGE (Social Agent Group Evolution),an evaluation framework that compares two compute-matched conditions: SocialEvo, where agents from five distinct model families co-evolve with access to all peers' histories; and SelfEvo, where each agent receives the same number of task attempts but sees only its own past, which is conventional in self-improving agent studies. We instantiate SAGE in three arenas: open-ended ML research, long-horizon economic planning, and strategic multiplayer play, evaluated across multiple evolutionary rounds. We find that group history is not a universal amplifier: the strongest agent does not exceed its self-evolution ceiling. However, agents that plateau under self-improvement can achieve significant breakthroughs when peer experience is available. In competitive settings, counterfactual controls reveal that agents improve generally rather than developing opponent-specific strategies. Across different forms of shared history, filtered peer traces and reflective summaries often outperform raw logs, indicating that social gains depend on abstraction rather than exposure volume. These findings reveal that peer-history gains are agent-specific, arena-dependent, and contingent on the capacity to abstract transferable knowledge from public traces.

Lingyue Fu, Xin Ding, Yaoming Zhu et al.

Large Language Model (LLM) agents have evolved from basic text generation to autonomously completing complex tasks through interaction with external tools. However, current benchmarks mainly assess end-to-end performance in fixed scenarios, restricting evaluation to specific skills and suffering from score saturation and growing dependence on expert annotation as agent capabilities improve. In this work, we emphasize the importance of learning ability, including both self-improvement and peer-learning, as a core driver for agent evolution toward human-level intelligence. We propose an iterative, competitive peer-learning framework, which allows agents to refine and optimize their strategies through repeated interactions and feedback, thereby systematically evaluating their learning capabilities. To address the score saturation issue in current benchmarks, we introduce CATArena, a tournament-style evaluation platform featuring four diverse board and card games with open-ended scoring. By providing tasks without explicit upper score limits, CATArena enables continuous and dynamic evaluation of rapidly advancing agent capabilities. Experimental results and analyses involving both minimal and commercial code agents demonstrate that CATArena provides reliable, stable, and scalable benchmarking for core agent abilities, particularly learning ability and strategy coding.

Shao Zhang, Xihuai Wang, Wenhao Zhang et al.

Agents built on large language models (LLMs) have excelled in turn-by-turn human-AI collaboration but struggle with simultaneous tasks requiring real-time interaction. Latency issues and the challenge of inferring variable human strategies hinder their ability to make autonomous decisions without explicit instructions. Through experiments with current independent System 1 and System 2 methods, we validate the necessity of using Dual Process Theory (DPT) in real-time tasks. We propose DPT-Agent, a novel language agent framework that integrates System 1 and System 2 for efficient real-time simultaneous human-AI collaboration. DPT-Agent's System 1 uses a Finite-state Machine (FSM) and code-as-policy for fast, intuitive, and controllable decision-making. DPT-Agent's System 2 integrates Theory of Mind (ToM) and asynchronous reflection to infer human intentions and perform reasoning-based autonomous decisions. We demonstrate the effectiveness of DPT-Agent through further experiments with rule-based agents and human collaborators, showing significant improvements over mainstream LLM-based frameworks. DPT-Agent can effectively help LLMs convert correct slow thinking and reasoning into executable actions, thereby improving performance. To the best of our knowledge, DPT-Agent is the first language agent framework that achieves successful real-time simultaneous human-AI collaboration autonomously. Code of DPT-Agent can be found in https://github.com/sjtu-marl/DPT-Agent.

Lingyue Fu, Hao Guan, Bolun Zhang et al.

As Large Language Models (LLMs) demonstrate increasingly sophisticated code processing capabilities, evaluating their performance on engineering-level code remains challenging. Existing repository-level benchmarks primarily focus on single scenarios, such as code generation or bug fixing, without adequately capturing the diversity and complexity of real-world software or project engineering workflows. Furthermore, these benchmarks suffer from limited controllability in question positioning and reliability issues in their generated test cases. To address these limitations, we present CorePipe, a fully automated pipeline that converts repositories into comprehensive test cases, and introduce CoreCodeBench, a configurable multi-scenario repository-level benchmark. To simulate real engineering scenarios, CorePipe generates three types of atomic questions (Development, BugFix, and Test-Driven Development) specifically targeting core code segments. These atomic questions are further combined into three types of composite questions, with difficulty levels flexibly adjusted through hyperparameter tuning. CoreCodeBench provides a comprehensive and extensive repository-level benchmark to investigate the applicability of LLMs in real-world engineering projects. Experiments with 16 LLMs across diverse scenarios reveal varying capabilities and offer multi-dimensional insights into LLM performance in engineering contexts. The code for CorePipe is available at https://github.com/AGI-Eval-Official/CoreCodeBench, and the data for CoreCodeBench can be accessed at https://huggingface.co/collections/tubehhh/corecodebench-68256d2faabf4b1610a08caa.

Peng Ding, Jun Kuang, Zongyu Wang et al.

Large Language Models (LLMs) have shown impressive capabilities across various tasks but remain vulnerable to meticulously crafted jailbreak attacks. In this paper, we identify a critical safety gap: while LLMs are adept at detecting jailbreak prompts, they often produce unsafe responses when directly processing these inputs. Inspired by this insight, we propose SAGE (Self-Aware Guard Enhancement), a training-free defense strategy designed to align LLMs' strong safety discrimination performance with their relatively weaker safety generation ability. SAGE consists of two core components: a Discriminative Analysis Module and a Discriminative Response Module, enhancing resilience against sophisticated jailbreak attempts through flexible safety discrimination instructions. Extensive experiments demonstrate SAGE's effectiveness and robustness across various open-source and closed-source LLMs of different sizes and architectures, achieving an average 99% defense success rate against numerous complex and covert jailbreak methods while maintaining helpfulness on general benchmarks. We further conduct mechanistic interpretability analysis through hidden states and attention distributions, revealing the underlying mechanisms of this detection-generation discrepancy. Our work thus contributes to developing future LLMs with coherent safety awareness and generation behavior. Our code and datasets are publicly available at https://github.com/NJUNLP/SAGE.

Peng Ding, Jun Kuang, Wen Sun et al.

Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing additional context or adversarial tokens, leaving the core harmful intent unchanged. In this paper, we introduce ISA (Intent Shift Attack), which obfuscates LLMs about the intent of the attacks. More specifically, we establish a taxonomy of intent transformations and leverage them to generate attacks that may be misperceived by LLMs as benign requests for information. Unlike prior methods relying on complex tokens or lengthy context, our approach only needs minimal edits to the original request, and yields natural, human-readable, and seemingly harmless prompts. Extensive experiments on both open-source and commercial LLMs show that ISA achieves over 70% improvement in attack success rate compared to direct harmful prompts. More critically, fine-tuning models on only benign data reformulated with ISA templates elevates success rates to nearly 100%. For defense, we evaluate existing methods and demonstrate their inadequacy against ISA, while exploring both training-free and training-based mitigation strategies. Our findings reveal fundamental challenges in intent inference for LLMs safety and underscore the need for more effective defenses. Our code and datasets are available at https://github.com/NJUNLP/ISA.

Zhejian Lai, Xiang Geng, Zhijun Wang et al.

Mathematical reasoning is a primary indicator of large language models (LLMs) intelligence. However, existing LLMs exhibit failures of robustness and generalization. This paper attributes these deficiencies to spurious reasoning, i.e., producing answers from superficial features. To address this challenge, we propose the AdaR framework to enable adaptive reasoning, wherein models rely on problem-solving logic to produce answers. AdaR synthesizes logically equivalent queries by varying variable values, and trains models with RLVR on these data to penalize spurious logic while encouraging adaptive logic. To improve data quality, we extract the problem-solving logic from the original query and generate the corresponding answer by code execution, then apply a sanity check. Experimental results demonstrate that AdaR improves robustness and generalization, achieving substantial improvement in mathematical reasoning while maintaining high data efficiency. Analysis indicates that data synthesis and RLVR function in a coordinated manner to enable adaptive reasoning in LLMs. Subsequent analyses derive key design insights into the effect of critical factors and the applicability to instruct LLMs. Our project is available at https://github.com/NJUNLP/AdaR.

Ziyan Liu, Junwen Li, Kaiwen Li et al.

Multimodal entity linking plays a crucial role in a wide range of applications. Recent advances in large language model-based methods have become the dominant paradigm for this task, effectively leveraging both textual and visual modalities to enhance performance. Despite their success, these methods still face two challenges, including unnecessary incorporation of image data in certain scenarios and the reliance only on a one-time extraction of visual features, which can undermine their effectiveness and accuracy. To address these challenges, we propose a novel LLM-based framework for the multimodal entity linking task, called Intra- and Inter-modal Collaborative Reflections. This framework prioritizes leveraging text information to address the task. When text alone is insufficient to link the correct entity through intra- and inter-modality evaluations, it employs a multi-round iterative strategy that integrates key visual clues from various aspects of the image to support reasoning and enhance matching accuracy. Extensive experiments on three widely used public datasets demonstrate that our framework consistently outperforms current state-of-the-art methods in the task, achieving improvements of 3.2%, 5.1%, and 1.6%, respectively. Our code is available at https://github.com/ziyan-xiaoyu/I2CR/.

Dan Ma, Jun Xu, Zongyu Wang et al.

Product reviews often contain a large number of implicit aspects and object-attribute co-existence cases. Unfortunately, many existing studies in Aspect-Based Sentiment Analysis (ABSA) have overlooked this issue, which can make it difficult to extract opinions comprehensively and fairly. In this paper, we propose a new task called Entity-Aspect-Opinion-Sentiment Quadruple Extraction (EASQE), which aims to hierarchically decompose aspect terms into entities and aspects to avoid information loss, non-exclusive annotations, and opinion misunderstandings in ABSA tasks. To facilitate research in this new task, we have constructed four datasets (Res14-EASQE, Res15-EASQE, Res16-EASQE, and Lap14-EASQE) based on the SemEval Restaurant and Laptop datasets. We have also proposed a novel two-stage sequence-tagging based Trigger-Opinion framework as the baseline for the EASQE task. Empirical evaluations show that our Trigger-Opinion framework can generate satisfactory EASQE results and can also be applied to other ABSA tasks, significantly outperforming state-of-the-art methods. We have made the four datasets and source code of Trigger-Opinion publicly available to facilitate further research in this area.

Yingxuan Yang, Bo Huang, Siyuan Qi et al.

Agentic workflows have become the dominant paradigm for building complex AI systems, orchestrating specialized components, such as planning, reasoning, action execution, and reflection, to tackle sophisticated real-world tasks. However, systematically analyzing and optimizing these workflows remains challenging due to intricate component interdependencies and the lack of principled attribution methods. In this work, we introduce ShapleyFlow, the first framework that employs cooperative game theory to analyze and optimize agentic workflows. By applying the Shapley value to evaluate all possible component configurations, ShapleyFlow enables fine-grained attribution of each component's contribution and facilitates the identification of task-specific optimal configurations. Through a constructed dataset evaluated across 7 scenarios, such as navigation, math and OS, we demonstrate 3 key contributions: (1) Theoretical Framework: a principled game-theoretic approach for the attribution of contributions in agentic workflows. (2) Optimal Workflow Discovery: ShapleyFlow identifies task-specific component configurations that consistently outperform workflows relying on a single LLM across all tested tasks. (3) Comprehensive Analysis: we construct and analyze over 1,500 tasks, providing actionable insights and design guidelines for optimizing workflows across multiple domains.

Zihao Zhao, Jiawei Chen, Sheng Zhou et al.

Recommender system usually suffers from severe popularity bias -- the collected interaction data usually exhibits quite imbalanced or even long-tailed distribution over items. Such skewed distribution may result from the users' conformity to the group, which deviates from reflecting users' true preference. Existing efforts for tackling this issue mainly focus on completely eliminating popularity bias. However, we argue that not all popularity bias is evil. Popularity bias not only results from conformity but also item quality, which is usually ignored by existing methods. Some items exhibit higher popularity as they have intrinsic better property. Blindly removing the popularity bias would lose such important signal, and further deteriorate model performance. To sufficiently exploit such important information for recommendation, it is essential to disentangle the benign popularity bias caused by item quality from the harmful popularity bias caused by conformity. Although important, it is quite challenging as we lack an explicit signal to differentiate the two factors of popularity bias. In this paper, we propose to leverage temporal information as the two factors exhibit quite different patterns along the time: item quality revealing item inherent property is stable and static while conformity that depends on items' recent clicks is highly time-sensitive. Correspondingly, we further propose a novel Time-aware DisEntangled framework (TIDE), where a click is generated from three components namely the static item quality, the dynamic conformity effect, as well as the user-item matching score returned by any recommendation model. Lastly, we conduct interventional inference such that the recommendation can benefit from the benign popularity bias while circumvent the harmful one. Extensive experiments on three real-world datasets demonstrated the effectiveness of TIDE.

Huichen Li, Xiaojun Xu, Chang Liu et al.

Malicious calls, i.e., telephony spams and scams, have been a long-standing challenging issue that causes billions of dollars of annual financial loss worldwide. This work presents the first machine learning-based solution without relying on any particular assumptions on the underlying telephony network infrastructures. The main challenge of this decade-long problem is that it is unclear how to construct effective features without the access to the telephony networks' infrastructures. We solve this problem by combining several innovations. We first develop a TouchPal user interface on top of a mobile App to allow users tagging malicious calls. This allows us to maintain a large-scale call log database. We then conduct a measurement study over three months of call logs, including 9 billion records. We design 29 features based on the results, so that machine learning algorithms can be used to predict malicious calls. We extensively evaluate different state-of-the-art machine learning approaches using the proposed features, and the results show that the best approach can reduce up to 90% unblocked malicious calls while maintaining a precision over 99.99% on the benign call traffic. The results also show the models are efficient to implement without incurring a significant latency overhead. We also conduct ablation analysis, which reveals that using 10 out of the 29 features can reach a performance comparable to using all features.

Minzhe Niu, Weinan Zhang, Yanru Qu et al.

Introducing consumed items as users' implicit feedback in matrix factorization (MF) method, SVD++ is one of the most effective collaborative filtering methods for personalized recommender systems. Though powerful, SVD++ has two limitations: (i). only user-side implicit feedback is utilized, whereas item-side implicit feedback, which can also enrich item representations, is not leveraged;(ii). in SVD++, the interacted items are equally weighted when combining the implicit feedback, which can not reflect user's true preferences accurately. To tackle the above limitations, in this paper we propose Graph-based collaborative filtering (GCF) model, Weighted Graph-based collaborative filtering (W-GCF) model and Attentive Graph-based collaborative filtering (A-GCF) model, which (i). generalize the implicit feedback to item side based on the user-item bipartite graph; (ii). flexibly learn the weights of individuals in the implicit feedback hence improve the model's capacity. Comprehensive experiments show that our proposed models outperform state-of-the-art models.For sparse implicit feedback scenarios, additional improvement is further achieved by leveraging the step-two implicit feedback information.