区分不确定性来源，才能让大模型更可信地表达不确定。
Why Don't You Know? Evaluating the Impact of Uncertainty Sources on Uncertainty Quantification in LLMs
- 构建新数据集，精准标注语言任务中的三类不确定性来源。
- 多数现有方法在知识不足时表现好，但面对输入模糊等其他来源时失效。
- 提醒开发者：评估模型信心前，先搞清不确定性来自哪里。
随着大语言模型在现实应用中日益普及，可靠的不确定性量化（UQ）对安全有效使用至关重要。现有大部分UQ方法仅输出单一置信度分数，例如模型答案正确的概率。然而自然语言任务中的不确定性源自多个不同层面，包括模型知识缺口、输出波动性及输入模糊性，这些差异对系统行为和用户交互具有不同影响。本文研究了不确定性来源如何影响现有UQ方法的表现。为实现可控分析，我们引入一个新数据集，明确分类不确定性来源，支持在每种条件下系统评估UQ性能。实验发现，尽管许多方法在仅由模型知识局限引起不确定性时表现良好，但当引入其他来源时，其性能下降或产生误导性结果。这一发现强调了需要开发能显式考虑不确定性来源的鲁棒方法。
原文摘要 · Abstract (English)
As Large Language Models (LLMs) are increasingly deployed in real-world applications, reliable uncertainty quantification (UQ) becomes critical for safe and effective use. Most existing UQ approaches for language models aim to produce a single confidence score -- for example, estimating the probability that a model's answer is correct. However, uncertainty in natural language tasks arises from multiple distinct sources, including model knowledge gaps, output variability, and input ambiguity, which have different implications for system behavior and user interaction. In this work, we study how the source of uncertainty impacts the behavior and effectiveness of existing UQ methods. To enable controlled analysis, we introduce a new dataset that explicitly categorizes uncertainty sources, allowing systematic evaluation of UQ performance under each condition. Our experiments reveal that while many UQ methods perform well when uncertainty stems solely from model knowledge limitations, their performance degrades or becomes misleading when other sources are introduced. These findings highlight the need for uncertainty-aware methods that explicitly account for the source of uncertainty in large language models.
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。