用贝叶斯方法减少大模型推理次数，高效找到最一致的答案。
Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
- 基于先验信息设计停机策略，仅追踪前3个最常见答案数。
- 实验显示可减少50%的调用次数，准确率与全量采样相当。
- 适合追求低成本高可靠推理的场景，尤其擅长数学与逻辑题。
提升大模型在数学和推理任务中准确率的一种简单方法是多次采样并取最一致的答案。本文利用贝叶斯先验信息，在达到足够一致性后即停止采样，以降低采样成本。尽管精确后验计算不可行，我们提出一种高效的“L-聚合”停机策略，仅需跟踪前L-1个最频繁答案的数量。理论上证明，L=3已足够：该粗略近似可实现渐近最优，且严格优于无先验基线，同时后验计算速度快。实验表明，该方法能以更少样本识别出最一致（即众数）的答案，在保持相近准确率的同时，将大模型调用次数减少高达50%。
原文摘要 · Abstract (English)
A simple strategy for improving LLM accuracy, especially in math and reasoning problems, is to sample multiple responses and submit the answer most consistently reached. In this paper we leverage Bayesian prior information to save on sampling costs, stopping once sufficient consistency is reached. Although the exact posterior is computationally intractable, we further introduce an efficient "L-aggregated" stopping policy that tracks only the L-1 most frequent answer counts. Theoretically, we prove that L=3 is all you need: this coarse approximation is sufficient to achieve asymptotic optimality, and strictly dominates prior-free baselines, while having a fast posterior computation. Empirically, this identifies the most consistent (i.e., mode) LLM answer using fewer samples, and can achieve similar answer accuracy while cutting the number of LLM calls (i.e., saving on LLM inference costs) by up to 50%.
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。