Reverse Prompting: A Novel Computational Paradigm in Schizophrenia Based on Large Language Models

Ivan Nenchev, Christiane Montag, Sandra Anna Just


Abstract
Large language models (LLMs) are increasingly being used to interpret and generate human language, yet their ability to process clinical language remains underexplored. This study examined whether three open-source LLMs can infer interviewer questions from participant responses in a semi-structured psychiatric interview (NET) conducted with individuals diagnosed with schizophrenia (n = 107) and neurotypical controls (n = 66). Using cosine similarity between LLM-generated questions and original prompts as a proxy for the precision of the inference, we found that responses from individuals with schizophrenia produced significantly lower similarity scores (beta = –0.165, p < .001). Cosine similarity decreased across the nested structure of the interview, with smaller reductions observed in the schizophrenia group. Although all emotions decreased similarity with fear, only sadness showed a significant interaction with diagnosis, suggesting differential processing of emotional discourse. Model type and generation temperature also influenced outcomes, highlighting variability in model performance. Our findings demonstrate that LLMs systematically struggle to reconstruct interviewer intent from responses by individuals with schizophrenia, reflecting known discourse-level disturbances in the disorder.
Anthology ID:
2025.ranlp-1.92
Volume:
Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Galia Angelova, Maria Kunilovskaya, Marie Escribe, Ruslan Mitkov
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
797–806
Language:
URL:
https://aclanthology.org/2025.ranlp-1.92/
DOI:
Bibkey:
Cite (ACL):
Ivan Nenchev, Christiane Montag, and Sandra Anna Just. 2025. Reverse Prompting: A Novel Computational Paradigm in Schizophrenia Based on Large Language Models. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 797–806, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Reverse Prompting: A Novel Computational Paradigm in Schizophrenia Based on Large Language Models (Nenchev et al., RANLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.ranlp-1.92.pdf