相信还是不相信您的LLM

摘要

我们探讨了大型语言模型（LLMs）中的不确定性量化，旨在确定在给定查询时响应的不确定性何时较大。我们同时考虑认知不确定性和随机不确定性，前者源于对基本事实（如事实或语言）的缺乏了解，后者源于不可减少的随机性（如多个可能的答案）。具体而言，我们推导了一种信息论度量标准，可以可靠地检测仅当认知不确定性较大时，模型的输出才是不可靠的。这种条件可以仅基于模型的输出计算，仅通过一些基于先前响应的特殊迭代提示获得。例如，这种量化可以检测出单个和多个答案响应中认知不确定性较高时的幻觉情况。这与许多标准不确定性量化策略形成对比（例如通过对响应的对数似然进行阈值处理），在多个答案情况下无法检测出幻觉。我们进行了一系列实验，证明了我们的公式的优势。此外，我们的研究揭示了大型语言模型分配给特定输出的概率如何通过迭代提示放大，这可能具有独立的研究意义。

English

We explore uncertainty quantification in large language models (LLMs), with the goal to identify when uncertainty in responses given a query is large. We simultaneously consider both epistemic and aleatoric uncertainties, where the former comes from the lack of knowledge about the ground truth (such as about facts or the language), and the latter comes from irreducible randomness (such as multiple possible answers). In particular, we derive an information-theoretic metric that allows to reliably detect when only epistemic uncertainty is large, in which case the output of the model is unreliable. This condition can be computed based solely on the output of the model obtained simply by some special iterative prompting based on the previous responses. Such quantification, for instance, allows to detect hallucinations (cases when epistemic uncertainty is high) in both single- and multi-answer responses. This is in contrast to many standard uncertainty quantification strategies (such as thresholding the log-likelihood of a response) where hallucinations in the multi-answer case cannot be detected. We conduct a series of experiments which demonstrate the advantage of our formulation. Further, our investigations shed some light on how the probabilities assigned to a given output by an LLM can be amplified by iterative prompting, which might be of independent interest.

相信还是不相信您的LLM

To Believe or Not to Believe Your LLM

摘要

Summary

Support

Support