教大模型真实表达不确定，答案更可信。
Teaching Language Models to Faithfully Express their Uncertainty
- 用一致性匹配的语气词训练模型，让不确定表达更真实。
- 显著缩小认知不确定性与回答表述间的差距。
- 适合作为提升模型可信度的通用增强方案。
大型语言模型常错误传达其不确定性：相同问题多次提问可能得到不同答案，但输出通常缺乏或不当使用模糊表达（如‘可能’‘大概’），导致对模型知识状态的失真描述，形成‘可信度缺口’。本文提出‘可信不确定性微调’（FUT）：一种无需改变原始回答分布的微调方法，通过在模型生成样本中添加与一致性匹配的语气词（如‘可能’‘很可能’），构建训练数据，仅需模型自身和一组提示，无需额外标注。在多个模型和开放域问答数据集上评估显示，FUT有效缩小可信度缺口，保持问答准确率，并引入极小的语义分布偏移。进一步分析表明，该方法对不同解码策略、语气词选择及数值形式的不确定性表达均具鲁棒性。结果证明FUT是一种简单有效的提升大模型不确定性表达可信度的方法。
原文摘要 · Abstract (English)
Large language models (LLMs) often miscommunicate their uncertainty: repeated queries can produce divergent answers, yet generated responses are typically unhedged or hedged in ways that do not reflect this variability. This conveys unfaithful information about the uncertain state of the LLMs' knowledge, creating a faithfulness gap that affects even strong LLMs. We introduce Faithful Uncertainty Tuning (FUT): a fine-tuning approach that teaches instruction-tuned LLMs to express uncertainty faithfully without altering their underlying answer distribution. We construct training data by augmenting model samples with uncertainty hedges (i.e. verbal cues such as 'possibly' or 'likely') aligned with sample consistency, requiring no supervision beyond the model and a set of prompts. We evaluate FUT on open-domain question answering (QA) across multiple models and datasets. Our results show that FUT substantially reduces the faithfulness gap, while preserving QA accuracy and introducing minimal semantic distribution shift. Further analyses demonstrate robustness across decoding strategies, choice of hedgers, and other forms of uncertainty expression (i.e. numerical). These findings establish FUT as a simple and effective way to teach LLMs to communicate uncertainty faithfully.
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。