BAS：一种基于决策理论的评估大语言模型置信度的方法
BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence
AI总结：
本文提出BAS，一种基于决策理论的评估方法，用于评估大语言模型置信度在不同风险偏好下的决策支持能力，揭示置信度与决策可靠性之间的关系，并展示如何通过干预提升置信度可靠性。
摘要：
大型语言模型（LLMs）在需要退避的场景中常常产生自信但错误的答案。然而，标准评估协议要求提供响应，并未考虑置信度如何指导不同风险偏好的决策。为此，我们引入了行为对齐分数（BAS），一种决策理论度量标准，用于评估LLM置信度在支持退避意识决策方面的表现。BAS源自一个显式的回答或退避效用模型，并在一系列风险阈值的连续范围内聚合实际效用，从而得到一个依赖于置信度幅度和顺序的决策层面可靠性度量。我们理论证明，真实置信度估计唯一最大化预期BAS效用，将校准与决策最优行为联系起来。BAS与诸如对数损失等适当评分规则相关，但结构上有所不同：对数损失对低估和高估对称惩罚，而BAS施加不对称惩罚，强烈优先避免高估错误。使用BAS与广泛使用的指标如ECE和AURC，我们构建了多个LLM和任务的自我报告置信度可靠性基准。我们的结果揭示了决策有用的置信度存在显著差异，尽管较大且更准确的模型倾向于获得较高的BAS，但前沿模型仍容易出现严重高估。重要的是，具有相似ECE或AURC的模型可以表现出非常不同的BAS，这突显了标准指标的局限性。我们进一步展示，简单的干预，如top-k置信度引导和事后校准，可以有意义地提高置信度可靠性。总体而言，我们的工作提供了评估LLM置信度可靠性的原理性度量和全面基准。
英文摘要：
Large language models (LLMs) often produce confident but incorrect answers in settings where abstention would be safer. Standard evaluation protocols, however, require a response and do not account for how confidence should guide decisions under different risk preferences. To address this gap, we introduce the Behavioral Alignment Score (BAS), a decision-theoretic metric for evaluating how well LLM confidence supports abstention-aware decision making. BAS is derived from an explicit answer-or-abstain utility model and aggregates realized utility across a continuum of risk thresholds, yielding a measure of decision-level reliability that depends on both the magnitude and ordering of confidence. We show theoretically that truthful confidence estimates uniquely maximize expected BAS utility, linking calibration to decision-optimal behavior. BAS is related to proper scoring rules such as log loss, but differs structurally: log loss penalizes underconfidence and overconfidence symmetrically, whereas BAS imposes an asymmetric penalty that strongly prioritizes avoiding overconfident errors. Using BAS alongside widely used metrics such as ECE and AURC, we then construct a benchmark of self-reported confidence reliability across multiple LLMs and tasks. Our results reveal substantial variation in decision-useful confidence, and while larger and more accurate models tend to achieve higher BAS, even frontier models remain prone to severe overconfidence. Importantly, models with similar ECE or AURC can exhibit very different BAS due to highly overconfident errors, highlighting limitations of standard metrics. We further show that simple interventions, such as top-$k$ confidence elicitation and post-hoc calibration, can meaningfully improve confidence reliability. Overall, our work provides both a principled metric and a comprehensive benchmark for evaluating LLM confidence reliability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
