通过不精确概率实现LLM的高阶不确定性 verbalizing
Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities
AI总结:
本文提出基于不精确概率的新型提示方法,用于更准确地提取LLM的高阶不确定性,以提升其不确定性和决策支持能力。
摘要:
尽管对从大型语言模型(LLMs)中提取不确定性的需求日益增长,但实证证据表明,LLM的行为并不总是被经典概率不确定性框架下开发的提取技术充分捕捉。这种不匹配导致了系统性的失败模式,特别是在涉及模糊问答、上下文学习和自我反思的设置中。为了解决这一问题,我们提出了基于提示的新型不确定性提取技术,这些技术建立在不精确概率的基础上,这是一种用于表示和提取高阶不确定性的原则性框架。在这里,一阶不确定性捕捉对提示可能响应的不确定性,而二阶不确定性(对不确定性的不确定性)量化了底层概率模型本身的不确定性。我们引入了通用的提示和后处理程序,直接提取并量化两种不确定性层次,并在多样化的设置中展示了其有效性。我们的方法使LLM能够更真实地报告不确定性,提高了可信度,并支持后续的决策制定。
英文摘要:
Despite the growing demand for eliciting uncertainty from large language models (LLMs), empirical evidence suggests that LLM behavior is not always adequately captured by the elicitation techniques developed under the classical probabilistic uncertainty framework. This mismatch leads to systematic failure modes, particularly in settings that involve ambiguous question-answering, in-context learning, and self-reflection. To address this, we propose novel prompt-based uncertainty elicitation techniques grounded in \emph{imprecise probabilities}, a principled framework for repesenting and eliciting higher-order uncertainty. Here, first-order uncertainty captures uncertainty over possible responses to a prompt, while second-order uncertainty (uncertainty about uncertainty) quantifies indeterminacy in the underlying probability model itself. We introduce general-purpose prompting and post-processing procedures to directly elicit and quantify both orders of uncertainty, and demonstrate their effectiveness across diverse settings. Our approach enables more faithful uncertainty reporting from LLMs, improving credibility and supporting downstream decision-making.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。