arXiv cs.AI· Hugues Draelants·· 1 天前AI 评分26
用大语言模型做理论原型与假设生成：定性实验室方法
The Qualitative Laboratory: Theory Prototyping and Hypothesis Generation with Large Language Models
AI 导读
一项案例研究用 LLM 扮演四个虚构角色，基于气候接受度矩阵回应燃油车禁售与气候正义进课程两组议题，共生成 32 条回复并分析其共性与分歧。结果显示 LLM 能把理论预设展开为情境化叙事并提出后续探究方向，但角色间相似度较高且对提示词构造敏感，作者提醒勿将话语连贯性误当社会学数据。该方法被定位为激发反思、打磨问题的启发式工具，而非用人工数据检验理论。
正文 · 原文
Abstract:The use of Large Language Models (LLMs) to simulate social actors has garnered attention for its implications for the epistemic status of discourses generated through such means. This paper considers the more modest question of whether sociological role-playing can serve as a heuristic instrument in the generation of qualitative hypotheses. We take as a case study the development of four divergent fictional characters using a theoretically informed Matrix of Climate Reception. These characters are asked to respond to a series of discourse frames covering two topics: a proposed ban on the sale of new gasoline-powered cars, and the inclusion of climate justice in the school curriculum. We then analyse the 32 model-generated responses for their commonalities, situational differences and divergences from the presuppositions underlying the characters' profiles. The experiment illustrates how LLMs can be used to flesh out theoretical presuppositions into contextual narratives and to propose avenues of further inquiry. It also shows that role-playing can generate considerable similarity between characters and is sensitive to how prompts are constructed, warning against the confusion of discursive coherence with sociological data. Role-playing is argued to be just one of several possible ways to use LLMs for generating hypotheses, with the heuristic specificity of this procedure compared with other methods of direct LLM-based reasoning or with other techniques remaining an open issue. The qualitative laboratory is thus conceived of as a heuristic instrument for provoking reflection and refining questions, not for testing theories with artificial data.
| Comments: | 27 pages, 3 tables. Unpublished manuscript |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Multiagent Systems (cs.MA) |
| ACM classes: | J.4; I.6.8; I.2.7 |
| Cite as: | arXiv:2601.00797 [cs.CL] |
| (or arXiv:2601.00797v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2601.00797 arXiv-issued DOI via DataCite |
Submission history
From: Hugues Draelants [view email]
[v1]
Tue, 25 Nov 2025 08:31:48 UTC (555 KB)
[v2]
Thu, 12 Nov 2026 18:19:34 UTC (420 KB)
来源：arXiv cs.AI · arxiv.org