Goto

Collaborating Authors

 rest -mct

ReST-MCTS: LLM Self-Training via Process Reward Guided Tree Search Dan Zhang

Neural Information Processing Systems

Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or intermediate reasoning).

ReST-MCTS: LLM Self-Training via Process Reward Guided Tree Search Dan Zhang

Neural Information Processing Systems

Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or intermediate reasoning).