EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning

ACL ARR 2025 May Submission2784 Authors

Abstract: Large Language Models (LLMs) excel at complex reasoning through search algorithms, yet current strategies often suffer from massive token consumption due to redundant exploration of semantically equivalent steps. Existing semantic similarity methods struggle to accurately identify such equivalence in domain-specific contexts like mathematical reasoning. To address this, we propose EquivPruner, a simple yet effective approach that identifies and prunes semantically equivalent actions during LLM reasoning search. We also introduce MathEquiv, the first dataset we created for mathematical statement equivalence, which enables the training of a lightweight equivalence detector. Extensive experiments across various models and tasks demonstrate that EquivPruner significantly reduces token consumption, improving searching efficiency and often bolstering reasoning accuracy. For instance, when applied to Qwen2.5-7B-Math-Instruct on GSM8K, EquivPruner reduced token consumption by 48.1\% while also improving accuracy. Our code is available at https://anonymous.4open.science/r/EquivPruner-2364/.

Paper Type: Long

Research Area: Efficient/Low-Resource Methods for NLP

Research Area Keywords: LLM Efficiency, reasoning, NLP datasets

Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models, Data resources, Data analysis

Languages Studied: English

Submission Number: 2784