用不确定性触发推理中断，提升大模型复杂问题求解能力
Partial Reasoning in Language Models: Search and Refinement Guided by Uncertainty
- 通过输出分布熵判断推理不确定性，动态触发局部精炼
- 在GSM8K等4个基准上表现优于或相当于软推理方法
- 适合需要高可靠推理的数学与逻辑任务场景
大型语言模型（LLMs）在推理与规划任务中日益受到关注。尽管取得显著进展，其在多步推理场景中仍存在局限，尤其是在数学与逻辑推理方面。本文提出PREGU（基于不确定性的部分推理），通过监控自回归生成过程中的输出分布熵，在熵超过阈值时停止生成，标志不确定性。随后在潜在空间进行局部搜索，利用软推理方法对部分推理结果进行精炼，选择最连贯的答案。在LLaMA-3-8B、Mistral-7B和Qwen2-7B上，针对GSM8K、GSM-Hard、SVAMP和StrategyQA四个推理基准的实验表明，该方法性能优于或相当於软推理，证明熵可作为有效信号，触发推理过程中的选择性精炼。
原文摘要 · Abstract (English)
The use of Large Language Models (LLMs) for reasoning and planning tasks has drawn increasing attention in Artificial Intelligence research. Despite their remarkable progress, these models still exhibit limitations in multi-step inference scenarios, particularly in mathematical and logical reasoning. We introduce PREGU (Partial Reasoning Guided by Uncertainty). PREGU monitors the entropy of the output distribution during autoregressive generation and halts the process whenever entropy exceeds a defined threshold, signaling uncertainty. From that point, a localized search is performed in the latent space to refine the partial reasoning and select the most coherent answer, using the Soft Reasoning method. Experiments conducted with LLaMA-3-8B, Mistral-7B, and Qwen2-7B across four reasoning benchmarks (GSM8K, GSM-Hard, SVAMP, and StrategyQA) showed performance greater than or similar to Soft Reasoning, indicating that entropy can serve as an effective signal to trigger selective refinement during reasoning.
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。