{"slug": "psyinterviewee-informational-invariance-and-relational-adaptivity-in-mental", "title": "PsyInterviewee: Informational Invariance and Relational Adaptivity in Mental Health Interview Simulation", "summary": "A new arXiv paper (2610.41289v1) introduces PsyInterviewee, an LLM-based simulated mental health interviewee that separates a protected truth channel from a dynamic interaction channel so dialogue context can update disclosure and behavioral states without authorizing new clinical facts. In automated evaluations of interactions between LLM-based interviewers and interviewees, PsyInterviewee scored higher than four representative baselines on most metrics across both informational invariance and relational adaptivity, as judged by two LLM judges, with ablations indicating the two channels contribute to clinical grounding and response modulation respectively.", "body_md": "arXiv:2610.41289v1 Announce Type: new \nAbstract: LLM-based simulated interviewees support interviewer training and the evaluation of mental health interviewing systems. Existing studies have primarily focused on improving human-likeness through richer patient profiles and behavioral modeling. However, human-likeness alone does not establish their reliability. Reliable simulation requires preserving profile-grounded clinical facts (informational invariance) while adapting disclosure and interaction behavior to the interview (relational adaptivity). To this end, we introduce PsyInterviewee, which separates a protected truth channel from a dynamic interaction channel and verifies generated clinical claims against the profile. Specifically, asymmetric write permissions allow dialogue context to update disclosure and behavioral states without authorizing new clinical facts; these states guide what profile-supported information is revealed and how it is expressed. In an automated evaluation of interactions between LLM-based interviewers and interviewees, PsyInterviewee achieves higher scores than four representative baselines on most metrics across both axes, as assessed by two LLM judges. Ablations suggest that the two channels contribute to clinical grounding and response modulation, respectively.", "url": "https://wpnews.pro/news/psyinterviewee-informational-invariance-and-relational-adaptivity-in-mental", "canonical_source": "https://arxiv.org/abs/2610.41289", "published_at": "2026-11-02 05:00:00+00:00", "updated_at": "2026-11-02 05:20:14.466986+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "ai-agents", "ai-safety"], "entities": ["PsyInterviewee", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/psyinterviewee-informational-invariance-and-relational-adaptivity-in-mental", "markdown": "https://wpnews.pro/news/psyinterviewee-informational-invariance-and-relational-adaptivity-in-mental.md", "text": "https://wpnews.pro/news/psyinterviewee-informational-invariance-and-relational-adaptivity-in-mental.txt", "jsonld": "https://wpnews.pro/news/psyinterviewee-informational-invariance-and-relational-adaptivity-in-mental.jsonld"}}