12 papers
Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning
Zezheng Wu, Xinghe Cheng, Qinggang Zhang +4
Machine unlearning aims to eliminate the influence of sensitive data on a model. In the real world, unlearning requests arrive continually, which gives rise to two challenges. Firs…
CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering
Zhichao Yan, Shizhao Li, Jiapu Wang +5
Long-form question answering increasingly relies on retrieved evidence to make LLM outputs verifiable, with inline citations tracing claims to source documents. However, existing s…
On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective
Yikai Guo, Bin Wang, Xilai Fan +2
AI-generated text increasingly blends with human writing, raising practical risks such as misinformation, academic misuse, and corpora contamination. While statistical detectors ar…
Rethinking Scientific Modeling: Toward Physically Consistent and Simulation-Executable Programmatic Generation
Yongqing Jiang, Jianze Wang, Zhiqi Shen +5
Structural modeling is a fundamental component of computational engineering science, in which even minor physical inconsistencies or specification violations may invalidate downstr…
MAXS: Meta-Adaptive Exploration with LLM Agents
Jian Zhang, Zhiyuan Wang, Zhangqi Wang +7
Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools. However, during agent inference, existing methods often suffer f…
Cumulative Path-Level Semantic Reasoning for Inductive Knowledge Graph Completion
Jiapu Wang, Xinghe Cheng, Zezheng Wu +6
Conventional Knowledge Graph Completion (KGC) methods aim to infer missing information in incomplete Knowledge Graphs (KGs) by leveraging existing information, which struggle to pe…
LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence
Wenjin Liu, Haoran Luo, Xin Feng +6
Legal general intelligence (GI) refers to artificial intelligence (AI) that encompasses legal understanding, reasoning, and decision-making, simulating the expertise of legal exper…
Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning
Wenjin Liu, Haoran Luo, Xueyuan Lin +5
Recently, advanced large language models (LLMs) have emerged at an increasingly rapid pace. However, when faced with complex problems, most users are often unable to provide accura…
MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses
Tong Chen, Zimu Wang, Yiyi Miao +6
Medical fact-checking has become increasingly critical as more individuals seek medical information online. However, existing datasets predominantly focus on human-generated conten…
From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning
Yichao Feng, Haoran Luo, Lang Feng +2
Large Language Models show promise in emotion understanding, social reasoning, and empathy, yet they struggle with psychologically grounded tasks that require inferring implicit me…
A Cognitive Writing Perspective for Constrained Long-Form Text Generation
Kaiyang Wan, Honglin Mu, Rui Hao +3
Like humans, Large Language Models (LLMs) struggle to generate high-quality long-form text that adheres to strict requirements in a single pass. This challenge is unsurprising, as…
CRE-LLM: A Domain-Specific Chinese Relation Extraction Framework with Fine-tuned Large Language Model
Zhengpeng Shi, Haoran Luo
Domain-Specific Chinese Relation Extraction (DSCRE) aims to extract relations between entities from domain-specific Chinese text. Despite the rapid development of PLMs in recent ye…