6 papers · 1 filter
Are Full Rollouts Necessary for On-Policy Distillation?
Yaocheng Zhang, Jiajun Chai, Yuqian Fu +7
On-policy distillation (OPD) provides dense teacher feedback along student-generated rollouts rather than fixed teacher traces and has emerged as a promising post-training paradigm…
PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review
Songjun Tu, Yiwen Ma, Jiahao Lin +6
Large language models can generate fluent peer reviews, yet their assessments often lack sufficient critical rigor when substantive issues are subtle and distributed across a paper…
AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
Di He, Songjun Tu, Ajay Jaiswal +4
Weight decay is a standard regularization technique for training large language models (LLMs). While it is common to assign a uniform decay rate to every layer, this approach overl…
Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL
Songjun Tu, Jiahao Lin, Qichao Zhang +4
Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce…
Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation
Songjun Tu, Jiahao Lin, Xiangyu Tian +8
Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. Ho…
SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
Yuqian Fu, Tinghong Chen, Jiajun Chai +7
Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remai…