查询时机在大型语言模型（LLMs）与人类之间产生相反的位置偏差
Query Timing Produces Opposite Positional Biases Between LLMs and Humans
- Princeton University（普林斯顿大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究探究查询时机对LLMs和人类位置偏差的影响，发现二者存在差异，且新LLMs的位置偏差比前代更显著。
AI中文摘要：
已有研究记录了大型语言模型（LLMs）中存在近因效应和首因效应等位置偏差，但这些模型进行评估的潜在机制仍知之甚少。人类在对证据进行判断时也会表现出首因和近因偏差，但近期研究表明，听众更新信念的时机——是在呈现证据的过程中还是仅在结束时——会影响这些效应是否存在。我们探究LLMs是否存在类似现象，发现其与人类行为存在差异。与前代模型相比，新模型的这些偏差更为显著。
英文摘要：
Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their evaluations remains poorly understood. Both primacy and recency biases have been observed in human judgments in response to evidence, but recent work suggest that \emph{when} the listener updates their beliefs -- during the presentation of evidence or only at the end -- influences the presence of such effects. We investigate whether a similar phenomenon holds for LLMs, finding divergence from human behavior. These biases are more exacerbated in newer models compared to their predecessors.
