---
title: "Spotting the Artificial: Dialogic Humor Improvisation in Humans and LLMs"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.00492v1"
permalink: "https://feed.astralor.com/items/itm_51ac9e6013104df6ec493809"
published: "2026-10-31T00:33:27.000Z"
score: 54
channel: "ai"
tags: ["LLM","AI Agent","Spotting","Artificial","Dialogic Humor Improvisation","Humans","LLMs","Our"]
---

# Spotting the Artificial: Dialogic Humor Improvisation in Humans and LLMs

## 速览

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 impr…

## 关键点

- 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).

## 全文

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

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_51ac9e6013104df6ec493809