用前缀一致性高效引导大模型推理，节省60%计算量。
The Path of Least Resistance: Guiding LLM Reasoning Trajectories with Prefix Consensus
- 通过聚类推理前缀识别主流路径，只扩展关键分支。
- 在多个数据集上媲美或超越自一致方法，减少60%令牌消耗。
- 可无缝集成现有加速技术，无需微调即可提升效率。
大型语言模型虽具备强大推理能力，但自一致（SC）等推断策略因需完整展开所有推理路径而计算开销巨大。本文提出PoLR（最小阻力路径），首个利用推理前缀一致性实现高效推断的方法。PoLR对推理路径的短前缀进行聚类，识别主导簇，并仅展开该簇内所有路径，在保持SC准确率优势的同时显著降低令牌使用量与延迟。理论分析基于互信息与熵，解释早期推理步骤蕴含强预测最终正确性的信号。实验表明，PoLR在GSM8K、MATH500、AIME24/25和GPQA-DIAMOND上持续匹配或超越SC，令牌使用量最高降低60%，墙钟延迟最高降低50%。此外，PoLR与自适应推断方法（如自适应一致性、早停自一致）完全互补，可作为即插即用的前置过滤器，使SC更高效、可扩展，且无需模型微调。
原文摘要 · Abstract (English)
Large language models achieve strong reasoning performance, but inference strategies such as Self-Consistency (SC) are computationally expensive, as they fully expand all reasoning traces. We introduce PoLR (Path of Least Resistance), the first inference-time method to leverage prefix consistency for compute-efficient reasoning. PoLR clusters short prefixes of reasoning traces, identifies the dominant cluster, and expands all paths in that cluster, preserving the accuracy benefits of SC while substantially reducing token usage and latency. Our theoretical analysis, framed via mutual information and entropy, explains why early reasoning steps encode strong signals predictive of final correctness. Empirically, PoLR consistently matches or exceeds SC across GSM8K, MATH500, AIME24/25, and GPQA-DIAMOND, reducing token usage by up to 60% and wall-clock latency by up to 50%. Moreover, PoLR is fully complementary to adaptive inference methods (e.g., Adaptive Consistency, Early-Stopping SC) and can serve as a drop-in pre-filter, making SC substantially more efficient and scalable without requiring model fine-tuning.
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。