activity
20242026
collaborators

8 papers

cs.CL2026

SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling

Haoran Xu, Hongyu Wang, Yifei Gao +3

On-policy distillation (OPD) trains a student on its own trajectories with dense per-token supervision from a stronger teacher, and often outperforms off-policy distillation and st…

cs.CV2026

Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning

Haoran Xu, Hongyu Wang, Yifei Gao +4

Visual reasoning requires integrating evidence distributed across regions, attributes, and relations, making single-chain reasoning prone to early perceptual commitment and halluci…

cs.AI2026

Reasoning Fails Where Step Flow Breaks

Xiaoyu Xu, Yulan Pan, Xiaosong Yuan +4

Large reasoning models (LRMs) that generate long chains of thought now perform well on multi-step math, science, and coding tasks. However, their behavior is still unstable and har…

cs.CL2026

ART: Attention Replacement Technique to Improve Factuality in LLMs

Ziqin Luo, Yihao Quan, Xiaofeng Zhang +2

Hallucination in large language models (LLMs) continues to be a significant issue, particularly in tasks like question answering, where models often generate plausible yet incorrec…

cs.AI2025

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning

Yue Xin, Chen Shen, Shaotian Yan +5

Chain-of-Thought (CoT) prompting enhances the math reasoning capability of large language models (LLMs) to a large margin. However, the mechanism underlying such improvements remai…

cs.CL2025

Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach

Sinan Fan, Liang Xie, Chen Shen +7

Prompt-tuning (PT) for large language models (LLMs) can facilitate the performance on various conventional NLP tasks with significantly fewer trainable parameters. However, our inv…