collaborators

7 papers

cs.CL2026

Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation

Bing Wang, Shaotian Yan, Chen Shen +7

Large language models (LLMs) have achieved remarkable success in complex reasoning tasks via long chain-of-thought (CoT), yet their immense computational overhead hinders real-worl…

cs.CL2026

On the Step Length Confounding in LLM Reasoning Data Selection

Bing Wang, Rui Miao, Chen Shen +7

Large reasoning models have recently demonstrated strong performance on complex tasks that require long chain-of-thought reasoning, through supervised fine-tuning on large-scale an…

cs.CV2026

Hallucination Begins Where Saliency Drops

Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu +8

Recent studies have examined attention dynamics in large vision-language models (LVLMs) to detect hallucinations. However, existing approaches remain limited in reliably distinguis…

cs.LG2026

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

Shaotian Yan, Kaiyuan Liu, Chen Shen +6

In this report, we introduce DASD-4B-Thinking, a lightweight yet highly capable, fully open-source reasoning model. It achieves SOTA performance among open-source models of compara…

cs.CV2025

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models

Qiyan Zhao, Xiaofeng Zhang, Yiheng Li +7

Hallucinations pose a significant challenge in Large Vision Language Models (LVLMs), with misalignment between multimodal features identified as a key contributing factor. This pap…

cs.CL2025

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning

Chenxi Huang, Shaotian Yan, Liang Xie +6

Representation Fine-tuning (ReFT), a recently proposed Parameter-Efficient Fine-Tuning (PEFT) method, has attracted widespread attention for significantly improving parameter effic…