activity
20242026
collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2026

TriggerBench: Investigating Prospective Memory for Large Language Models

Tianhua Zhang, Xinjiang Wang, Qianxi Zhang +6

While Large Language Models (LLMs) are increasingly deployed in long interactions, existing evaluations focus predominantly on retrospective memory (RM) via explicit queries. Prosp…

cs.CL2026

TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAG

Tianhua Zhang, Kun Li, Junan Li +5

Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval, and has recently been advanced b…

cs.CL2025

RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning

Kun Li, Yunxiang Li, Tianhua Zhang +4

Robust evaluation is critical for deploying trustworthy retrieval-augmented generation (RAG) systems. However, current LLM-based evaluation frameworks predominantly rely on directl…

cs.CL2025

Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution

Kun Li, Tianhua Zhang, Yunxiang Li +5

Improving context faithfulness in large language models is essential for developing trustworthy retrieval augmented generation systems and mitigating hallucinations, especially in…

cs.CL2024

Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains

Kun Li, Tianhua Zhang, Xixin Wu +3

Knowledge Graphs (KGs) can serve as reliable knowledge sources for question answering (QA) due to their structured representation of knowledge. Existing research on the utilization…

cs.CL2024

Purple-teaming LLMs with Adversarial Defender Training

Jingyan Zhou, Kun Li, Junan Li +4

Existing efforts in safeguarding LLMs are limited in actively exposing the vulnerabilities of the target LLM and readily adapting to newly emerging safety risks. To address this, w…