Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ruan, Zhiwen, Li, Yixia, Zhu, He, Chen, Yun, Li, Peng, Liu, Yang, Chen, Guanhua
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908589189234688
author Ruan, Zhiwen
Li, Yixia
Zhu, He
Chen, Yun
Li, Peng
Liu, Yang
Chen, Guanhua
author_facet Ruan, Zhiwen
Li, Yixia
Zhu, He
Chen, Yun
Li, Peng
Liu, Yang
Chen, Guanhua
contents Large language models (LLMs) primarily rely on supervised fine-tuning (SFT) as a key method to adapt pre-trained models to domain-specific tasks such as mathematical reasoning. However, standard SFT uniformly penalizes all tokens, neglecting that only a small subset of critical tokens determines reasoning correctness. This uniform supervision often causes reduced output diversity and limited generalization. We propose Critical Token Fine-tuning (CFT), a simple yet effective approach that updates only tokens identified as functionally indispensable via counterfactual perturbations. By focusing gradient signals on these decisive reasoning steps while preserving the diversity of non-critical tokens, CFT can enhance both generation and diversity. Extensive experiments on five models across three families (Qwen, OLMo, LLaMA) and eleven mathematical reasoning benchmarks show that CFT, despite fine-tuning on less than 12% of tokens, consistently outperforms standard SFT. Moreover, CFT enables test-time scaling through improved sampling diversity and provides a stronger initialization for reinforcement learning, sustaining performance gains in later training stages while maintaining higher entropy for better exploration. These results highlight CFT as a practical and general framework for efficient and robust LLM fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10974
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning
Ruan, Zhiwen
Li, Yixia
Zhu, He
Chen, Yun
Li, Peng
Liu, Yang
Chen, Guanhua
Computation and Language
Large language models (LLMs) primarily rely on supervised fine-tuning (SFT) as a key method to adapt pre-trained models to domain-specific tasks such as mathematical reasoning. However, standard SFT uniformly penalizes all tokens, neglecting that only a small subset of critical tokens determines reasoning correctness. This uniform supervision often causes reduced output diversity and limited generalization. We propose Critical Token Fine-tuning (CFT), a simple yet effective approach that updates only tokens identified as functionally indispensable via counterfactual perturbations. By focusing gradient signals on these decisive reasoning steps while preserving the diversity of non-critical tokens, CFT can enhance both generation and diversity. Extensive experiments on five models across three families (Qwen, OLMo, LLaMA) and eleven mathematical reasoning benchmarks show that CFT, despite fine-tuning on less than 12% of tokens, consistently outperforms standard SFT. Moreover, CFT enables test-time scaling through improved sampling diversity and provides a stronger initialization for reinforcement learning, sustaining performance gains in later training stages while maintaining higher entropy for better exploration. These results highlight CFT as a practical and general framework for efficient and robust LLM fine-tuning.
title Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning
topic Computation and Language
url https://arxiv.org/abs/2510.10974