EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentation

2026-01-07

arXiv.org

AI Summary

This work addresses a critical flaw in existing chain-of-thought (CoT) fine-tuning data, where correct final answers are often accompanied by flawed intermediate reasoning—such as hallucinations, redundancies, or logical errors. To mitigate this, the authors propose EntroCoT, a novel framework that introduces entropy-guided dynamic reasoning segmentation and step-level marginal contribution evaluation. Specifically, EntroCoT adaptively partitions reasoning trajectories using information entropy and employs Monte Carlo rollouts to quantify each step’s contribution to the final answer, enabling automatic filtering of low-quality samples. Experiments across multiple mathematical reasoning benchmarks demonstrate that models fine-tuned on high-quality CoT datasets curated by EntroCoT significantly outperform those trained on full original datasets, highlighting the effectiveness of the proposed approach in enhancing reasoning fidelity and model performance.

Technology Category

• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Chain-of-Thought (CoT) prompting has significantly enhanced the mathematical reasoning capabilities of Large Language Models. We find existing fine-tuning datasets frequently suffer from the"answer right but reasoning wrong"probelm, where correct final answers are derived from hallucinated, redundant, or logically invalid intermediate steps. This paper proposes EntroCoT, a unified framework for automatically identifying and refining low-quality CoT supervision traces. EntroCoT first proposes an entropy-based mechanism to segment the reasoning trace into multiple steps at uncertain junctures, and then introduces a Monte Carlo rollout-based mechanism to evaluate the marginal contribution of each step. By accurately filtering deceptive reasoning samples, EntroCoT constructs a high-quality dataset where every intermediate step in each reasoning trace facilitates the final answer. Extensive experiments on mathematical benchmarks demonstrate that fine-tuning on the subset constructed by EntroCoT consistently outperforms the baseslines of full-dataset supervision.

Problem

• Chain-of-Thought
• reasoning quality
• hallucination
• fine-tuning dataset
• mathematical reasoning

Innovation

• Chain-of-Thought
• entropy-based segmentation
• Monte Carlo rollout
• reasoning quality filtering
• large language models