arXiv cs.CL· Ruoxi Su, Yuhan Liu, Jingyu Hu·· 12 小时前AI 评分52
研究：一小时 LLM 访谈只能提取性格特质，无法预测个人决策
What a One-Hour Interview Does Not Tell an LLM About You: Interviews Elicit Traits, Not Decision Policies
AI 导读
一项 arXiv 论文测试一小时 LLM 主导的自适应访谈能告诉模型多少关于个人价值取向决策的信息：46 名成年人完成访谈后回答 25 道两难问题作为真实答案，结果显示访谈任何部分都不比无信息基线和多数答案基线更可靠，自适应追问也不优于固定问题。
正文 · 原文
Abstract:Large language models are increasingly asked to stand in for particular people, and interviewing the person is the natural way to tell a model who they are. We test what a one-hour LLM-led adaptive interview tells a model about an individual's value-laden decisions. 46 adults completed such an interview and then answered 25 dilemma questions, which are the ground truth. We predict their answers from different parts of the transcript, compare adaptive follow-up questions with fixed ones on the same participants, and benchmark every variant against a model given no information about the person and against the majority answer. No part of the interview is reliably better than either baseline, and adaptive follow-ups are no better than fixed ones. Two audits of the transcripts show why. For 85% of the errors an auditor finds no evidence that distinguishes the person's choice from the alternatives, and where a transcript does contain related evidence, the option it favours matches the person's own answer less often than the majority answer does. The same transcripts do improve recovery of the person's MBTI type. Interviews of this kind elicit traits, not decision policies. We discuss what decision-aware elicitation would require and why persona agents should not be delegated value-laden decisions, and we release the consenting participants' transcripts with all predictions.
| Comments: | 25 pages, 5 figures, 27 tables. Substantially revised version: new title, a second cohort (N=46), a within-subject fixed follow-up control, zero-context and majority baselines, and two transcript audits |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.7 |
| Cite as: | arXiv:2605.29458 [cs.CL] |
| (or arXiv:2605.29458v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.29458 arXiv-issued DOI via DataCite |
Submission history
From: Ruoxi Su [view email]
[v1]
Thu, 28 May 2026 06:53:08 UTC (347 KB)
[v2]
Tue, 20 Oct 2026 05:05:53 UTC (123 KB)
来源：arXiv cs.CL · arxiv.org