发表机构
Northwestern University（西北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出决策理论框架，将LLM决策损失分解为信念形成与行动优化，通过合成基准诊断概率推理，发现联合干预信念与决策可改进性能但依赖格式匹配。
AI 中文摘要
大型语言模型（LLMs）日益被提议作为决策助手，它们必须在明确的决策成本下，根据现有证据进行概率推理。我们提出一个决策理论框架，将LLMs的决策损失分解为两个组成部分：从提供的证据中形成准确的信念，以及将这些信念转化为优化给定效用函数的行动。利用一个具有已知真实标签的合成基准，我们应用该分解来表征前沿和开源模型中的概率推理。我们进一步评估针对信念、决策或两者的强化学习干预是否能在三个领域改进这些组成部分，改进是否能在组成部分和提示格式之间转移，以及决策性能是否能在信念形成未改进的情况下得到提升。我们发现，针对概率推理的一个组成部分会重新分配决策损失，改进目标而不一定转移到其他组成部分，并且联合针对信念形成和决策制定能同时改进两者，但依赖于训练与评估之间的格式匹配。
英文摘要
Large language models (LLMs) are increasingly proposed as decision assistants who must reason probabilistically from available evidence under explicit decision costs. We propose a decision-theoretic framework that decomposes LLMs' decision loss into two components: forming accurate beliefs from provided evidence and translating those beliefs into actions that optimize a provided utility function. Using a synthetic benchmark with known ground truth, we apply the decomposition to characterize probabilistic reasoning in frontier and open-sourced models. We further evaluate whether RL interventions targeting beliefs, decisions, or both improve these components across three domains, whether improvements transfer across components and elicitation formats, and whether decision performance can improve without improvement in belief formation. We find that targeting one component of probabilistic reasoning redistributes decision loss, improving the target without necessarily transferring to others, and that jointly targeting belief formation and decision-making improves both but hinges on matched formats between training and evaluation.
