works on

From the 1 of 9 linked papers with an AI index.

collaborators
Showing cs.CLShow all

7 papers · 1 filter

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

TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning

Xiaosong Han, Ke Chen, Xindi Dai +7

In real-world deployment, LLMs are often adapted continually across tasks to keep LLMs up-to-date in production, where new fine-tuning should preserve previously learned skills. Ho…

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.CL2025

DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF

Ziyuan Gao, Di Liang, Xianjie Wu +2

Existing reinforcement learning methods for Chain-of-Thought reasoning suffer from two critical limitations. First, they operate as monolithic black boxes that provide undifferenti…

cs.CL2025

Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance

Yao Wang, Di Liang, Minlong Peng

Supervised fine-tuning (SFT) is a pivotal approach to adapting large language models (LLMs) for downstream tasks; however, performance often suffers from the ``seesaw phenomenon'',…