用博弈论方法量化语言模型输出的不确定性，更精准判断何时该信任答案。
Shapley Uncertainty in Natural Language Generation
- 基于博弈论的谢尔普利值构建连续性不确定性度量
- 在问答任务中比基线方法更准确预测模型表现
- 适合需要可信推理的AI系统开发者使用
在问答任务中，判断何时信任大语言模型（LLMs）的输出对模型对齐至关重要。Kuhn等人（2023）提出语义熵作为不确定性度量，通过引入同义表达的语言不变性来衡量。该方法主要依赖阈值判断语义等价程度。本文提出一种更精细的框架，超越阈值设定，构建基于谢尔普利值的不确定性度量，以捕捉语义关系的连续特性。我们确立了刻画有效不确定性度量的三个基本性质，并证明所提出的谢尔普利不确定性满足这些条件。通过大量实验，验证了该度量在问答及其他数据集上比现有基线方法更准确地预测大语言模型性能。
原文摘要 · Abstract (English)
In question-answering tasks, determining when to trust the outputs is crucial to the alignment of large language models (LLMs). Kuhn et al. (2023) introduces semantic entropy as a measure of uncertainty, by incorporating linguistic invariances from the same meaning. It primarily relies on setting threshold to measure the level of semantic equivalence relation. We propose a more nuanced framework that extends beyond such thresholding by developing a Shapley-based uncertainty metric that captures the continuous nature of semantic relationships. We establish three fundamental properties that characterize valid uncertainty metrics and prove that our Shapley uncertainty satisfies these criteria. Through extensive experiments, we demonstrate that our Shapley uncertainty more accurately predicts LLM performance in question-answering and other datasets, compared to similar baseline measures.
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。