用语言冗余度精准删减大模型推理过程，省时提效不丢智商。
Verbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled Criteria
- 基于概率和冗余度判定，按句子级别删减推理内容。
- 平均提升性能7.71%，生成tokens减少19.87%。
- 适合追求高效推理的工业级应用与资源受限场景。
大型语言模型（LLMs）依赖生成大量中间推理单元（如标记、句子）以提升复杂任务的最终答案质量。尽管有效，但显著增加推理开销。以往无明确标准的逐令牌删减方法，导致性能低于完整推理路径训练的模型。为此，本文提出一种基于似然性准则的句级推理删减框架，利用冗余度（verbosity）识别并移除冗余推理句，保留核心推理能力。在多个推理任务上的实验表明，该方法相较完整推理路径训练模型，平均性能提升7.71%，同时减少19.87%的生成token数。
原文摘要 · Abstract (English)
Large Language Models (LLMs) rely on generating extensive intermediate reasoning units (e.g., tokens, sentences) to enhance final answer quality across a wide range of complex tasks. While this approach has proven effective, it inevitably increases substantial inference costs. Previous methods adopting token-level reduction without clear criteria result in poor performance compared to models trained with complete rationale. To address this challenge, we propose a novel sentence-level rationale reduction framework leveraging likelihood-based criteria, verbosity, to identify and remove redundant reasoning sentences. Unlike previous approaches, our method leverages verbosity to selectively remove redundant reasoning sentences while preserving reasoning capabilities. Our experimental results across various reasoning tasks demonstrate that our method improves performance by an average of 7.71% while reducing token generation by 19.87% compared to model trained with complete reasoning paths.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。