Can I read BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation on EtoBox?

BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation by Pang, Bo; Dong, Hanze; Xu, Jiacheng; Savarese, Silvio; Zhou, Yingbo; Xiong, Caiming is a scholarly article available to read on EtoBox.

What is BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation about?

Large language models (LLMs), such as o1 from OpenAI, have demonstrated remarkable reasoning capabilities. o1 generates a long chain-of-thought (LongCoT) before answering a question. LongCoT allows LLMs to analyze problems, devise plans, reflect, and backtrack effectively. These actions empower LLM to solve complex problems. After the release of o1, many teams have attempted to replicate its LongCoT and reasoning capabilities. In terms of methods, they primarily rely on knowledge distillation with data from existing models with LongCoT capacities (e.g., OpenAI-o1, Qwen-QwQ, DeepSeek-R1-Preview), leaving significant uncertainties on systematically developing such reasoning abilities. In terms of data domains, these works focus narrowly on math while a few others include coding, limiting their generalizability. This paper introduces a novel approach to enable LLM's LongCoT capacity without distillation from o1-like models or expensive human annotations, where we bootstrap LongCoT (BOLT) from a standard instruct model. BOLT involves three stages: 1) LongCoT data bootstrapping with in-context learning on a standard instruct model; 2) LongCoT supervised finetuning; 3) online training to

Author

Pang, Bo; Dong, Hanze; Xu, Jiacheng; Savarese, Silvio; Zhou, Yingbo; Xiong, Caiming

Published

2025

Language

EN