Frontiers in Psychiatry 研究：上下文呈现方式影响大模型对升级自杀风险的识别

ORIGINAL RESEARCH article

Front. Psychiatry

Sec. Digital Mental Health

Abstract

Background: Large language models are increasingly used for informal mental health support, yet their safety during escalating suicide-risk conversations may depend on how prior information is presented. Native multi-turn conversations and reconstructed cumulative prompts differ not only in the presence of prior model responses but also in prompt reconstruction, information concentration, message positioning, explicit integration cues, and conversation-state processing. Objective: This study compared suicide-risk recognition, direct safety inquiry, response urgency, and timely real-world intervention across isolated current-turn prompts, reconstructed cumulative user-only prompts, and native continuous multi-turn conversations. Methods: We conducted a controlled repeated-measures evaluation of ChatGPT, Gemini, and Doubao using 12 standardized five-turn trajectories: 4 direct suicide-risk trajectories, 4 implicit or internally inconsistent risk trajectories, and 4 non-suicidal high-distress controls. Each trajectory was evaluated under three context-presentation formats. The 24 model-trajectory combinations were treated as matched repeated-measures units nested within 8 independent risk-trajectory blocks. Primary contrasts were estimated using exact trajectory-level sign-flip tests and trajectory-block bootstrap confidence intervals. Turn-level outcomes were analyzed using multilevel mixed-effects models. Exploratory condition-by-model heterogeneity was assessed using a trajectory-blocked exact permutation sensitivity analysis, with a trajectory-clustered interaction model used only as a secondary asymptotic check. Results: Timely appropriate intervention occurred in 10/24 isolated current-turn observations (41.7%), 21/24 reconstructed cumulative observations (87.5%), and 12/24 native continuous observations (50.0%). On average across the three systems, reconstructed cumulative presentation exceeded isolated input by 45.8 percentage points (95% trajectory-block bootstrap CI, 25.0 to 66.7; Holm-adjusted exact P=.031), whereas native continuous performance was 37.5 percentage points lower than reconstructed cumulative performance (95% trajectory-block bootstrap CI, −50.0 to −25.0; Holm-adjusted exact P=.031). Conclusions: On average across the three evaluated systems, reconstructed cumulative user-only prompts outperformed native continuous conversations, although exploratory model-specific patterns were heterogeneous. Because the formats also differed in prompt reconstruction, information salience, message positioning, explicit integration instructions, and native conversation-state processing, the contrast cannot isolate the causal effect of prior model responses.

Keywords

context presentation, conversational safety, digital mental health, Large language models, native multi-turn conversation, suicide risk

Received

08 August 2026

Accepted

23 September 2026

Copyright

© 2026 Xiao, Chen, Cai, Luo and Deng. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Correspondence: Jiehua Deng

Disclaimer

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

• Outline
• Share
• Metrics
• More