38 citations · 48 across the 27 of their papers we have counts for
29 papers
EnGRICH: Enhancing Generative Reward Modeling with Critiques from Humans
Xuancheng Li, Beining Wang, Haitao Li +7
Generative reward models (GRMs) are important for LLM optimization. Unlike scalar reward models, GRMs generate natural-language critiques alongside preference judgments, providing…
Composable Parametric Demographic Injection for Values Survey Simulation
Xinyuan Cao, Qingyi Pan, Bangde Du +7
Large language models (LLMs) are increasingly used as simulated respondents in computational social science, yet accurately reproducing population-specific heterogeneous response d…
Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories
Hexi Wang, Yujia Zhou, Bangde Du +7
Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed. Existing methods can partially reproduce p…
Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models
Xuancheng Li, Xuanchen Li, Haitao Li +6
User feedback offers natural supervision for persistent LLM improvement, but a single message may support multiple behavioral changes with different scopes of generalization. We in…
MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio
Anzhe Xie, Weihang Su, Yujia Zhou +3
Systematic review and meta-analysis is an important method for scientific research. It comprehensively studies target research questions by combining evidence from multiple indepen…
Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation
Junjie Chen, Yuxi Dong, Haitao Li +5
As large language models (LLMs) are increasingly used for long-form generation, reliably evaluating long-form outputs has become a critical challenge. LLM-as-a-judge offers a scala…
How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
Shuqi Zhu, Yi Zhong, Ziyi Ye +4
While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled by these hallucinations remai…
Parametric Social Identity Injection and Diversification in Public Opinion Simulation
Hexi Wang, Yujia Zhou, Bangde Du +2
Large language models (LLMs) have recently been adopted as synthetic agents for public opinion simulation, offering a promising alternative to costly and slow human surveys. Despit…
ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs
Xuancheng Li, Haitao Li, Yujia Zhou +2
Long-context inputs in large language models (LLMs) often suffer from the "lost in the middle" problem, where critical information becomes diluted or ignored due to excessive lengt…
LegalOne: A Family of Foundation Models for Reliable Legal Reasoning
Haitao Li, Yifan Chen, Shuo Miao +13
While Large Language Models (LLMs) have demonstrated impressive general capabilities, their direct application in the legal domain is often hindered by a lack of precise domain kno…
Beyond Exposure: Optimizing Ranking Fairness with Non-linear Time-Income Functions
Xuancheng Li, Tao Yang, Yujia Zhou +2
Ranking systems in web search and recommendation allocate attention among items and providers, and therefore need to balance relevance-based effectiveness with provider fairness. E…
Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
Xuancheng Li, Haitao Li, Yujia Zhou +2
Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on external retrieval, which is similarity-base…
MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn Loop
Xuancheng Li, Haitao Li, Yujia Zhou +2
Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning across domains, but outcome-only scalar rewards are often sparse and uninformative. This l…
TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation
Bangde Du, Minghao Guo, Songming He +8
Large Language Models (LLMs) are exhibiting emergent human-like abilities and are increasingly envisioned as the foundation for simulating an individual's communication style, beha…
Generalized Pseudo-Relevance Feedback
Yiteng Tu, Weihang Su, Yujia Zhou +4
Query rewriting is a fundamental technique in information retrieval (IR). It typically employs the retrieval result as relevance feedback to refine the query and thereby addresses…
From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization
Beining Wang, Weihang Su, Hongtao Tian +5
Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLV…
Simulating Dispute Mediation with LLM-Based Agents for Legal Research
Junjie Chen, Haitao Li, Minghao Qin +6
Legal dispute mediation plays a crucial role in resolving civil disputes, yet its empirical study is limited by privacy constraints and complex multivariate interactions. To addres…
Chinese Court Simulation with LLM-Based Agent System
Kaiyuan Zhang, Jiaqi Li, Yueyue Wu +7
Mock trial has long served as an important platform for legal professional training and education. It not only helps students learn about realistic trial procedures, but also provi…
ValueSim: Generating Backstories to Model Individual Value Systems
Bangde Du, Ziyi Ye, Zhijing Wu +5
As Large Language Models (LLMs) continue to exhibit increasingly human-like capabilities, aligning them with human values has become critically important. Contemporary advanced tec…
Augmenting Multi-Agent Communication with State Delta Trajectory
Yichen Tang, Weihang Su, Yujia Zhou +4
Multi-agent techniques such as role playing or multi-turn debates have been shown to be effective in improving the performance of large language models (LLMs) in downstream tasks.…
Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
Changyue Wang, Weihang Su, Qingyao Ai +2
Knowledge editing aims to efficiently update Large Language Models (LLMs) by modifying specific knowledge without retraining the entire model. Among knowledge editing approaches, i…
Investigating Prosocial Behavior Theory in LLM Agents under Policy-Induced Inequities
Yujia Zhou, Hexi Wang, Qingyao Ai +2
As large language models (LLMs) increasingly operate as autonomous agents in social contexts, evaluating their capacity for prosocial behavior is both theoretically and practically…
RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects
Yiteng Tu, Weihang Su, Yujia Zhou +2
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamen…
Parametric Retrieval Augmented Generation
Weihang Su, Yichen Tang, Qingyao Ai +6
Retrieval-augmented generation (RAG) techniques have emerged as a promising solution to enhance the reliability of large language models (LLMs) by addressing issues like hallucinat…