This work introduces SPEAR (Self-Play Enhancement via Advantage-Weighted Refinement), an efficient online learning algorithm for federated LLM fine-tuning that requires only an interaction-level binary satisfaction signal together with non-answer feedback, without requiring a ground-truth answer to be provided, and doe...
Seohyun Lee, Wen-Zhi Fang, Dong-Jun Han et al.· arXiv.org· 1 citation
Tory of Scene (ToS), a training-free reasoning schema in which each agent reads its public role, the only difference between the agents, and the task context they all observe, is proposed, which outperforms all six baselines on every benchmark, and each baseline falls far behind it in at least one setting.
Liang-Qi Yuan, Wen-Zhi Fang, Shi-Qiang Wang et al.· arXiv.org· 1 citation
Reinforcement learning (RL)-based post-training has become an effective approach for eliciting reasoning capabilities in large language models (LLMs). However, adapting post-RL models to new knowledge domains or behaviors through subsequent supervised fine-tuning (SFT) can severely overwrite these capabilities. Existin...
Wen-Zhi Fang, Nicholas Tzou, L. Valkov et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.