5 papers
Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis
Mutian Yang, Zisen Zhan, Yutong Chen +7
Catastrophic forgetting during knowledge injection impairs the ability of large language models to acquire new knowledge without overwriting previously mastered knowledge. Recent s…
Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
Jingyuan Xie, Wenjie Wang, Ji Wu +1
Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly focused on the detectable backdoor at…
CoScale-RL: Efficient Post-Training by Co-Scaling Data and Computation
Yutong Chen, Jiandong Gao, Ji Wu
Training Large Reasoning Model (LRM) is usually unstable and unpredictable, especially on hard problems or weak foundation models. We found that the current post-training scaling s…
Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning
Yutong Chen, Jiandong Gao, Ji Wu
R1-style Reinforcement Learning (RL) significantly enhances Large Language Models' reasoning capabilities, yet the mechanism behind rule-based RL remains unclear. We found that sma…
Decoupling Knowledge and Reasoning in LLMs: An Exploration Using Cognitive Dual-System Theory
Mutian Yang, Jiandong Gao, Ji Wu
While large language models (LLMs) leverage both knowledge and reasoning during inference, the capacity to distinguish between them plays a pivotal role in model analysis, interpre…