大型语言模型中的不连贯概率判断
Incoherent Probability Judgments in Large Language Models
AI总结：
本文通过概率恒等式和重复判断实验发现大型语言模型的概率判断常不连贯且呈类似人类的倒U形均值-方差关系，并提出可用隐式贝叶斯推断与贝叶斯采样器模型解释这些偏离。
摘要：
经过下一词预测训练的自回归大型语言模型（LLMs）在生成连贯文本方面表现出卓越的能力。但它们是否同样擅长形成连贯的概率判断？我们使用概率恒等式和重复判断来评估大型语言模型所做概率判断的连贯性。我们的结果表明，这些模型产生的判断往往是不连贯的，表现出类似人类的对概率论规则的系统性偏离。此外，当被提示判断同一事件时，大型语言模型产生的概率判断的均值-方差关系呈现出与人类相似的倒U形。我们提出，这些对理性的偏离可以通过将自回归大型语言模型与隐式贝叶斯推断联系起来，并与人类概率判断的贝叶斯采样器模型进行类比来解释。
英文摘要：
Autoregressive Large Language Models (LLMs) trained for next-word prediction have demonstrated remarkable proficiency at producing coherent text. But are they equally adept at forming coherent probability judgments? We use probabilistic identities and repeated judgments to assess the coherence of probability judgments made by LLMs. Our results show that the judgments produced by these models are often incoherent, displaying human-like systematic deviations from the rules of probability theory. Moreover, when prompted to judge the same event, the mean-variance relationship of probability judgments produced by LLMs shows an inverted-U-shaped like that seen in humans. We propose that these deviations from rationality can be explained by linking autoregressive LLMs to implicit Bayesian inference and drawing parallels with the Bayesian Sampler model of human probability judgments.
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。
