Mufan Xu — accepted AI-conference papers

2026

User-Aware Active Knowledge Acquisition for Emotional Support Dialogue

Mufan Xu, Kehai Chen, Jiahao Hu, Xinchao Xu, Muyun Yang, Tiejun Zhao +1

ICML 2026poster

Emotional support plays an important role in dialogue systems, and its success depends on adapting to a user’s evolving and implicit needs across multi-turn interactions while leveraging the strong reasoning capacity of large language models (LLMs). However, since user needs are often weakly supervi…

Cited by 0 Source ↗Scholar ↗

2025

Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning

Mufan Xu, Gewen Liang, Kehai Chen, Wei Wang, Xun Zhou, Muyun Yang +2

ACL 2025finding

Large language models (LLMs) have achieved remarkable performance on knowledge graph question answering (KGQA) tasks by planning and interacting with knowledge graphs. However, existing methods often confuse tool utilization with knowledge reasoning, harming readability of model outputs and giving r…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗