1 citations · 1 across the 5 of their papers we have counts for
4 papers · 1 filter
BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning
Keshu Fu, Keqin Peng, Jun Bai +6
Large language models often improve task performance by generating long reasoning traces, but the resulting computation is frequently wasted on redundant verification and revision.…
Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation
Keqin Peng, Chen Li, Yuanxin Ouyang +2
On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs). However, in complex reasoning tasks, OPSD paradoxicall…
PFME: A Modular Approach for Fine-grained Hallucination Detection and Editing of Large Language Models
Kunquan Deng, Zeyu Huang, Chen Li +3
Large Language Models (LLMs) excel in fluency but risk producing inaccurate content, called "hallucinations." This paper outlines a standardized process for categorizing fine-grain…
How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey
Jun Bai, Xiaofeng Zhang, Chen Li +4
Transferability estimation has been attached to great attention in the computer vision fields. Researchers try to estimate with low computational cost the performance of a model wh…