arXiv cs.AI· Marcin Moskalewicz, Anna Sterna, Karolina Dro\.zd\.z, Kacper Dudzic, Marek Pokropski, Paula Flores·· 4 小时前AI 评分42
GPT、Gemini 与 Claude 模拟专家人格辅助边缘型人格障碍临床定性分析的比较研究
Computational Phenomenology of Borderline Personality Disorder: A Comparative Evaluation of LLM-Simulated Expert Personas and Human Clinical Experts
AI 导读
一项研究基于对边缘型人格障碍住院患者逾 150,000 词临床访谈的主题分析，评估 GPT、Gemini 与 Claude 支持定性临床分析的能力。AI 分析与人类解读的主题重叠度为 0-58%，但所有模型都发现了人类研究者遗漏的主题。盲评中 Gemini 2.5 Pro 的内容效度与人类专家无异，其语义向量嵌入风格也最接近人类。
正文 · 原文
Abstract:Building on a human-led thematic analysis of clinical life-story interviews (> 150,000 words) with inpatients with Borderline Personality Disorder, this study examines the capacity of large language models (OpenAI's GPT, Google's Gemini, and Anthropic's Claude) to support qualitative clinical analysis. The models' interpretative potential was evaluated using a mixed-methods approach. Study A involved blinded and non-blinded judges in phenomenology and clinical psychology. The experts assessed the validity of AI-generated content using semantic congruence, Jaccard coefficients, and multidimensional validity ratings, including credibility, coherence, the substantiveness of results, and grounding in qualitative data. In Study B, neural methods were used to embed human- and model-generated theme descriptions in a multidimensional vector space. This approach provided an objectified computational measure of the difference between human and model semantics and linguistic style. In Study C, complementary non-expert evaluations were conducted (N=115) to examine the influence of thematic verbosity on the perception of human authorship and content validity. Overall, the results of AI analysis showed a highly variable overlap (0-58%) with the human interpretation, while all models identified themes originally omitted by human researchers, proving their capacity to mitigate human bias. At the thematic level, external evaluators were unable to reliably distinguish human-authored themes from those generated by AI. In terms of content validity assessed against raw data by high-level experts in the blinded mode, the performance of Gemini 2.5 Pro was indistinguishable from that of humans. The comparison of semantic vector embeddings showed that its style was also the closest to humans.
| Comments: | Accepted to the Proceedings of the First Workshop on Ethics in Clinical AI Applications (ETHICAIA 2026) co-located with the 35th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026). 28 pages, 8 tables, 2 figures |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| ACM classes: | I.2.7; J.3 |
| Cite as: | arXiv:2508.19008 [cs.AI] |
| (or arXiv:2508.19008v4 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2508.19008 arXiv-issued DOI via DataCite |
|
| Journal reference: | CEUR Workshop Proceedings, Vol. 4306, pp. 73-100 (2026) |
Submission history
From: Kacper Dudzic [view email]
[v1]
Tue, 26 Aug 2025 13:13:47 UTC (548 KB)
[v2]
Mon, 26 Jan 2026 15:37:22 UTC (314 KB)
[v3]
Thu, 20 Aug 2026 13:44:56 UTC (503 KB)
[v4]
Wed, 4 Nov 2026 15:25:44 UTC (503 KB)
来源：arXiv cs.AI · arxiv.org