重新思考大语言模型不确定性：一种估计黑盒模型不确定性的多智能体方法
Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty
AI总结：
针对现有黑盒LLM不确定性自一致性评估方法易受上下文偏差误导的问题，提出基于多智能体多样化查询交互的DiverseAgentEntropy方法，可更准确评估真实不确定性并提升幻觉检测性能。
摘要：
量化黑盒大语言模型（LLM）的不确定性对于生成可靠响应和实现可扩展监督至关重要。现有方法通过评估模型对目标查询响应的自一致性来衡量其不确定性，这类方法可能产生误导：LLM可能对某一目标查询给出高置信度的错误答案，但在回答该查询的知识保持型扰动版本时，却能给出高置信度且准确的答案。我们系统分析了模型行为，证明这种差异源于参数知识的检索次优，通常是由上下文偏差导致模型无法一致访问存储的知识所致。随后我们提出DiverseAgentEntropy，这是一种具备理论基础的新方法，通过在多样化查询变体上开展多智能体交互来估计黑盒LLM的不确定性。该方法能更准确地评估LLM的真实不确定性，提升幻觉检测效果，性能优于现有的基于自一致性的技术。
英文摘要：
Quantifying uncertainty in black-box LLMs is vital for reliable responses and scalable oversight. Existing methods, which gauge a model's uncertainty through evaluating self-consistency in responses to the target query, can be misleading: an LLM may confidently provide an incorrect answer to a target query, yet give a confident and accurate answer to that same target query when answering a knowledge-preserving perturbation of the query. We systematically analyze the model behaviors and demonstrate that this discrepancy stems from suboptimal retrieval of parametric knowledge, often due to contextual biases that prevent consistent access to stored knowledge. We then introduce DiverseAgentEntropy, a novel, theoretically-grounded method employing multi-agent interaction across diverse query variations for uncertainty estimation of black-box LLMs. This approach more accurately assesses an LLM's true uncertainty and improves hallucination detection, outperforming existing self-consistency based techniques.
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。
