Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification
arxiv(2024)
摘要
Large language models (LLMs) are notorious for hallucinating, i.e., producing
erroneous claims in their output. Such hallucinations can be dangerous, as
occasional factual inaccuracies in the generated text might be obscured by the
rest of the output being generally factual, making it extremely hard for the
users to spot them. Current services that leverage LLMs usually do not provide
any means for detecting unreliable generations. Here, we aim to bridge this
gap. In particular, we propose a novel fact-checking and hallucination
detection pipeline based on token-level uncertainty quantification. Uncertainty
scores leverage information encapsulated in the output of a neural network or
its layers to detect unreliable predictions, and we show that they can be used
to fact-check the atomic claims in the LLM output. Moreover, we present a novel
token-level uncertainty quantification method that removes the impact of
uncertainty about what claim to generate on the current step and what surface
form to use. Our method Claim Conditioned Probability (CCP) measures only the
uncertainty of particular claim value expressed by the model. Experiments on
the task of biography generation demonstrate strong improvements for CCP
compared to the baselines for six different LLMs and three languages. Human
evaluation reveals that the fact-checking pipeline based on uncertainty
quantification is competitive with a fact-checking tool that leverages external
knowledge.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要