7 papers
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…
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…
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…
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…
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…
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…