arXiv cs.CL· Lizeth Palacios Pati\~no, Ximena Gutierrez-Vasques, Daniel Rodriguez·· 11 小时前AI 评分31
人类与 LLM 即兴幽默对话对比：LLM 难以复现自发言语互动特征
Spotting the Artificial: Dialogic Humor Improvisation in Humans and LLMs
AI 导读
一项新研究比较多智能体环境中 LLM 生成的对话与人类喜剧即兴表演，发现 LLM 虽能构建连贯且有创意的场景，却常无法复现自发言语互动的关键特征。LLM 生成的互动还明显偏向礼貌和正面评价，与人类幽默即兴中更广泛的态度形成反差。该研究结合自动语言指标与基于系统功能语言学（SFL）的人工标注，凸显当前 LLM 在对话式幽默建模上的优势与局限。
正文 · 原文
Abstract:We propose a methodology for investigating the differences between natural and synthetic language in a challenging setting: humorous improvisational dialogue. Our experimental setting compares human-produced comedy improvisations with the dialogues generated by LLMs in a multi-agent environment that we designed. The analysis combines automated linguistic measures with manual annotation grounded in Systemic Functional Linguistics (SFL).
The results show that, although LLMs can create coherent and creative scenes, they often fail to reproduce key characteristics of spontaneous spoken interaction. In addition, LLM-generated interactions display a strong tendency toward politeness and positive evaluations, contrasting with the broader range of attitudes found in human humorous improvisation. Our evidence highlights both the strengths and limitations of current LLMs in modeling dialogic humor and demonstrate the value of integrating linguistic theory with NLP methods for the analysis of machine-generated language
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.00492 [cs.CL] |
| (or arXiv:2611.00492v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.00492 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Springer Nature Link. MICAI 2026, CCIS,Part I proceeding |
Submission history
From: Ximena Gutierrez-Vasques [view email]
[v1]
Sat, 31 Oct 2026 00:33:27 UTC (4,840 KB)
来源：arXiv cs.CL · arxiv.org