通过迭代采样优化答案分布，提升大模型推理准确性
Refining Answer Distributions for Improved Large Language Model Reasoning
- 构建基于蒙特卡洛近似的迭代采样框架，动态聚焦高概率答案
- 在多个推理基准上显著优于自一致性等现有方法
- 适合需要高精度推理的复杂任务场景
大语言模型在执行推理任务时表现出色，尤其是当被引导生成一系列中间步骤时。通过合理组合多个模型响应（可并行或串行生成），可进一步提升推理性能。然而，现有的组合策略如自一致性与渐进提示法对模型输出的利用效率较低。本文提出一种新颖且理论严谨的算法框架——精炼答案分布（Refined Answer Distributions），将其视为对潜在答案分布的蒙特卡洛逼近，通过迭代采样寻找最可能的答案（即分布的众数）。在多个推理基准上的实证评估表明，该方法具有显著优势。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have exhibited an impressive capability to perform reasoning tasks, especially if they are encouraged to generate a sequence of intermediate steps. Reasoning performance can be improved by suitably combining multiple LLM responses, generated either in parallel in a single query, or via sequential interactions with LLMs throughout the reasoning process. Existing strategies for combination, such as self-consistency and progressive-hint-prompting, make inefficient usage of the LLM responses. We present Refined Answer Distributions, a novel and principled algorithmic framework to enhance the reasoning capabilities of LLMs. Our approach can be viewed as an iterative sampling strategy for forming a Monte Carlo approximation of an underlying distribution of answers, with the goal of identifying the mode -- the most likely answer. Empirical evaluation on several reasoning benchmarks demonstrates the superiority of the proposed approach.
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。