评估评估指标——幻觉检测的幻象
Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection
AI总结：
本文评估了6种幻觉检测指标在4个数据集、37个语言模型和5种解码方法上的表现，发现现有指标与人类判断不一致，且参数规模影响不一致，LLM评估和模式寻求解码方法能有效减少幻觉。
摘要：
幻觉是语言模型可靠性和广泛应用的主要障碍，但其准确测量仍是个挑战。本文对6种幻觉检测指标在4个数据集、37个语言模型和5种解码方法上进行了大规模实证评估。研究发现当前幻觉评估指标存在明显缺陷：指标常与人类判断不一致，问题视角过于狭隘，参数规模影响不一致。鼓励的是，基于LLM的评估，特别是GPT-4，表现出最佳整体结果，模式寻求解码方法似乎能减少幻觉，尤其是在知识导向的设置中。这些发现强调了需要更稳健的指标来理解和量化幻觉，以及更好的策略来缓解它们。
英文摘要：
Hallucinations pose a significant obstacle to the reliability and widespread adoption of language models, yet their accurate measurement remains a persistent challenge. While many task- and domain-specific metrics have been proposed to assess faithfulness and factuality concerns, the robustness and generalization of these metrics are still untested. In this paper, we conduct a large-scale empirical evaluation of 6 diverse sets of hallucination detection metrics across 4 datasets, 37 language models from 5 families, and 5 decoding methods. Our extensive investigation reveals concerning gaps in current hallucination evaluation: metrics often fail to align with human judgments, take an overtly myopic view of the problem, and show inconsistent gains with parameter scaling. Encouragingly, LLM-based evaluation, particularly with GPT-4, yields the best overall results, and mode-seeking decoding methods seem to reduce hallucinations, especially in knowledge-grounded settings. These findings underscore the need for more robust metrics to understand and quantify hallucinations, and better strategies to mitigate them.
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。
