通过分布正确性衡量大语言模型幻觉
When Guessing is Rewarded: Rethinking Language Model Evaluation with Distributional Uncertainty Scoring
AI总结:
针对现有语言模型评估未完整考量概率分布的缺陷,提出分布正确性得分DCS以区分有害过度自信与合理弃权,实验显示多数被测模型在半数基准上呈负分,幻觉倾向显著。
摘要:
当前大语言模型的常见评估范式聚焦于通过准确率指标或恰当评分规则对单个回复打分,无法捕捉模型信念状态的全部丰富信息。近期研究表明,大语言模型产生幻觉的部分原因在于,其被优化为二元评分机制下的“优秀应试者”——这类机制会奖励任何作答而非弃权(不执行)。尽管这一洞见自然催生了基于惩罚的方法,但这类方法忽略了模型分配不确定性方式的关键差异,例如,朝错误答案摇摆的不确定性与朝“我不知道”回复摇摆的不确定性之间的区别。\n为解决未考虑模型在所有选项上的完整概率分布这一问题,本文提出了一种新型评估指标——分布正确性得分(Distributional Correctness Score, DCS)。DCS能够自然区分对错误答案的有害过度自信与通过弃权(不执行)表达的不确定性,且得分处于可解释的默认范围内。通过理论分析与示例验证,DCS被证明能提供更细致、更对齐的评估范式,可激励模型表达真实不确定性而非猜测。\n研究将12个现有评估基准适配到DCS的变体上,并在6个大语言模型上测试性能,结果显示:在半数测试基准中,所有被测模型的得分均为负值,表明其存在显著的幻觉倾向。
英文摘要:
Standard language model evaluation assigns scores to single predicted answers, rewarding high-confidence responses regardless of how residual probability mass is distributed over alternative options. This creates a systematic pressure toward overconfident guessing: under accuracy-based schemes, a model maximises its expected score by always committing to an answer rather than abstaining, even when its uncertainty is high. While penalty-based approaches partially address this by raising the confidence threshold for strategic guessing, they still treat all sub-threshold responses identically, ignoring a fundamental distinction in how models can express uncertainty - for example between hedging toward incorrect answers versus hedging toward "I don't know" responses. This paper introduces a novel evaluation metric to solve this problem of not considering a model's entire probability distribution over answer choices. The metric naturally distinguishes between harmful overconfidence in wrong answers and uncertainty expressed through abstention, providing scores in an interpretable default range. Through theoretical analysis and illustrative examples, the metric is shown to offer a more nuanced and aligned evaluation paradigm that incentivises models to express genuine uncertainty rather than guessing. Adapting 12 existing evaluation benchmarks to the metric's variants and measuring performance on six language models shows that for half of the tested benchmarks scores are negative across all tested models, indicating significant tendencies towards hallucination.
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。