发表机构
MIT; NBER; University of Chicago（麻省理工学院; 美国国家经济研究局; 芝加哥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文基于德菲内蒂定理构建流程，以股票收益数据生成的事件为样本，用线性规划计算最大荷兰赌利润衡量语言模型概率预测的自洽性，发现其存在大量自洽性不足的情况，并探讨了改善策略。
AI 中文摘要
人们越来越多地使用语言模型来支持生活决策，其中许多决策涉及概率预测：重大生活事件、自然灾害或经济结果的发生概率是多少？语言模型的用户可能会默认相信这些预测源自一个自洽的世界模型。在本文中，我们基于德菲内蒂（de Finetti）的一个定理构建流程，来评估语言模型概率预测的自洽性。我们从股票收益数据生成的各类事件中获取语言模型的预测结果，随后运用线性规划计算最大荷兰赌利润——即套利者通过对模型生成的概率下注可确保获得的利润，并将其作为自洽性的衡量指标。我们的流程无需结果标签，因此即便在结果未被观测或尚未确定的场景中，也能评估自洽性。我们发现语言模型预测存在大量自洽性不足的证据；当事件间存在更丰富的逻辑关系时，这种自洽性不足会加剧，而无关的上下文细节可使自洽性不足的程度提升一个数量级。最后，我们探讨了替代训练策略如何改善概率自洽性。
英文摘要
People increasingly use language models to support life decisions. Many such decisions involve a probabilistic forecast: How likely is a major life event, a natural disaster, or an economic outcome? Users of language models may implicitly trust that these forecasts fall out of a coherent world model. In this paper, we evaluate the coherence of language model probabilistic forecasts through a procedure that builds on a theorem due to de Finetti. We elicit forecasts from language models across events generated from stock returns data. We then use linear programs to compute the largest Dutch-book profit - the profit an arbitrageur could guarantee by betting against model-generated probabilities - which we use as a measure of incoherence. Our procedure does not require outcome labels, so we can evaluate coherence even in settings where outcomes are not observed or have not yet resolved. We find substantial evidence of incoherence in language model forecasts. Such incoherence increases when there are richer logical relationships between events, and irrelevant contextual details can increase incoherence by an order of magnitude. We conclude by discussing how alternative training strategies may improve probabilistic coherence.
Comments14 pages, 6 figures
