提出双指标框架，让大模型自知回答可信度。
A Context-Aware Dual-Metric Framework for Confidence Estimation in Large Language Models
- 用上下文信息增益衡量数据不确定性
- 在多个数据集上比现有方法提升可信度评估效果
- 适合需要高可靠性输出的场景
准确的置信度估计对可信赖的大语言模型系统至关重要，它帮助用户判断何时应信任输出，并支持在安全关键应用中的可靠部署。当前的LLM置信度估计方法忽视了回答与上下文信息的相关性，而这一因素在提供背景知识的场景中尤为关键。为此，我们提出CRUX（上下文感知熵缩减与统一一致性检验），首个融合上下文忠实性与一致性的置信度估计框架，包含两个新指标：上下文熵缩减通过对比有无上下文时的采样信息增益来表征数据不确定性；统一一致性检验则通过生成答案在有无上下文时的全局一致性捕捉模型不确定性。在CoQA、SQuAD、QuAC三个基准数据集及BioASQ、EduQG两个领域特定数据集上的实验表明，CRUX在所有测试中均达到最高AUROC值，显著优于现有基线方法。
原文摘要 · Abstract (English)
Accurate confidence estimation is essential for trustworthy large language models (LLMs) systems, as it empowers the user to determine when to trust outputs and enables reliable deployment in safety-critical applications. Current confidence estimation methods for LLMs neglect the relevance between responses and contextual information, a crucial factor in output quality evaluation, particularly in scenarios where background knowledge is provided. To bridge this gap, we propose CRUX (Context-aware entropy Reduction and Unified consistency eXamination), the first framework that integrates context faithfulness and consistency for confidence estimation via two novel metrics. First, contextual entropy reduction represents data uncertainty with the information gain through contrastive sampling with and without context. Second, unified consistency examination captures potential model uncertainty through the global consistency of the generated answers with and without context. Experiments across three benchmark datasets (CoQA, SQuAD, QuAC) and two domain-specific datasets (BioASQ, EduQG) demonstrate CRUX's effectiveness, achieving the highest AUROC than existing baselines.
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。