基于LLM的贝叶斯 elicitation:模型大小有帮助,额外“推理”并不总有效
Bayesian Elicitation with LLMs: Model Size Helps, Extra "Reasoning" Doesn't Always
AI总结:
本文研究了LLM在贝叶斯 elicitation中的表现,发现更大模型更准确,但增加推理不总是有帮助。所有模型严重过度自信,95%置信区间覆盖真实值比例远低于预期,统计校准技术可修正此问题。
摘要:
大型语言模型(LLMs)已被提出作为替代人类专家来估计未知量及其不确定性,这一过程称为贝叶斯 elicitation。我们通过让11个LLM估计人口统计数据,如健康普及率、人格特质分布和劳动力市场数据,并以95%置信区间表达不确定性来测试这一方法。我们通过改变每个模型的推理努力程度(低、中、高)来检验更多“思考”是否能提高结果。我们的发现揭示了三个关键结果。首先,更大、更强大的模型产生更准确的估计,但增加推理努力没有一致的益处。其次,所有模型严重过度自信:它们的95%置信区间只在9-44%的时间内包含真实值,远低于预期的95%。第三,一种称为符合预测的统计校准技术可以纠正这种过度自信,通过扩展置信区间以实现预期的覆盖。在初步实验中,给模型提供网络搜索访问权会降低已准确模型的预测,但对较弱的模型有适度的改善。模型在常见话题上表现良好,但在专业健康数据上挣扎。这些结果表明,在决策中使用LLM的不确定性估计需要统计校准。
英文摘要:
Large language models (LLMs) have been proposed as alternatives to human experts for estimating unknown quantities with associated uncertainty, a process known as Bayesian elicitation. We test this by asking eleven LLMs to estimate population statistics, such as health prevalence rates, personality trait distributions, and labor market figures, and to express their uncertainty as 95\% credible intervals. We vary each model's reasoning effort (low, medium, high) to test whether more "thinking" improves results. Our findings reveal three key results. First, larger, more capable models produce more accurate estimates, but increasing reasoning effort provides no consistent benefit. Second, all models are severely overconfident: their 95\% intervals contain the true value only 9--44\% of the time, far below the expected 95\%. Third, a statistical recalibration technique called conformal prediction can correct this overconfidence, expanding the intervals to achieve the intended coverage. In a preliminary experiment, giving models web search access degraded predictions for already-accurate models, while modestly improving predictions for weaker ones. Models performed well on commonly discussed topics but struggled with specialized health data. These results indicate that LLM uncertainty estimates require statistical correction before they can be used in 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。