collaborators

5 papers

cs.CL2026

UXBench: Benchmarking User Experience in AI Assistants

Mengze Hong, Xia Zeng, Zeyang Lei +26

UXBench is a user‑centric benchmark that uses real interaction logs to evaluate how well AI assistants align with user preferences and generate engaging dialogue, featuring three t…

cs.CL2026

Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty

Chao Xue, Yao Wang, Mengqiao Liu +11

Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Thought (CoT) prompting. Despit…

cs.CL2026

Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models

Chao Xue, Yao Wang, Mengqiao Liu +11

Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after conve…

cs.LG2026

Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning

Zekai Lin, Chao Xue, Di Liang +8

Supervised Fine-Tuning (SFT) of large language models often suffers from task interference and catastrophic forgetting. Recent approaches alleviate this issue by isolating task-cri…

cs.CL2025

TableBench: A Comprehensive and Complex Benchmark for Table Question Answering

Xianjie Wu, Jian Yang, Linzheng Chai +10

Recent advancements in Large Language Models (LLMs) have markedly enhanced the interpretation and processing of tabular data, introducing previously unimaginable capabilities. Desp…