collaborators

6 papers

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.CL2026

DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning

Xiaoyu Liu, Xiaoyu Guan, Di Liang +1

Supervised fine-tuning (SFT) is a crucial step for adapting large language models (LLMs) to downstream tasks. However, conflicting objectives across heterogeneous SFT tasks often i…

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.AI2025

Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling

Xiaoyu Liu, Di Liang, Chang Dai +9

Reward Models (RMs) are key components for evaluating and guiding language model outputs. However, traditional scalar RMs often struggle with incorporating contextual and backgroun…