arXiv cs.CL· Catherine Bao, Vivek Srikumar·· 12 小时前AI 评分31
LLM 是否共享人类时间错觉？新基准测试 14 个模型
The Machine's Internal Clock: Do LLMs Share Human Temporal Illusions?
AI 导读
研究团队构建了含 6,684 个配对场景、覆盖五种时间错觉的基准，测试纯文字叙事能否引发人类时间错觉以及 LLM 是否与人类判断一致。60 名人类参与者在 10 个条件中的 7 个（每种错觉至少一个视角）判断方向符合预期；14 个 LLM 均复现了人类全部效应的同向结果，但平均强度更高。
正文 · 原文
Abstract:Human perception of time is subjective. Temporal illusions show that the brain relies on context and relational cues when judging duration. Prior studies established these effects with visual and auditory stimuli. We ask whether written narratives alone can cause these illusions, and whether LLMs respond as human participants do. We introduce a benchmark of 6,684 paired scenarios spanning five illusions, each judged from the character's and the reader's perspective. In our human study (60 participants), participants' judgments matched the predicted directions for all five illusions in at least one perspective (7 of 10 conditions). Across 14 LLMs, models reproduce every effect humans show in the same direction, but on average more strongly. Most effects persisted even after cue words were removed and after controlling for 15 lexical and semantic features. These results show that models and humans agree in direction but not in strength, which cautions against treating LLM judgments as substitutes for human responses for subjective temporal reasoning.
| Comments: | 27 pages, 19 figures |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2608.15394 [cs.CL] |
| (or arXiv:2608.15394v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.15394 arXiv-issued DOI via DataCite |
Submission history
From: Catherine Bao Bao [view email]
[v1]
Sat, 15 Aug 2026 19:54:49 UTC (6,532 KB)
[v2]
Mon, 19 Oct 2026 23:41:34 UTC (5,978 KB)
来源：arXiv cs.CL · arxiv.org