@inproceedings{nenchev-etal-2025-reverse,
title = "Reverse Prompting: A Novel Computational Paradigm in Schizophrenia Based on Large Language Models",
author = "Nenchev, Ivan and
Montag, Christiane and
Just, Sandra Anna",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.92/",
pages = "797--806",
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 {\ensuremath{<}} .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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nenchev-etal-2025-reverse">
<titleInfo>
<title>Reverse Prompting: A Novel Computational Paradigm in Schizophrenia Based on Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Nenchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christiane</namePart>
<namePart type="family">Montag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="given">Anna</namePart>
<namePart type="family">Just</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 \ensuremath< .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.</abstract>
<identifier type="citekey">nenchev-etal-2025-reverse</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.92/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>797</start>
<end>806</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reverse Prompting: A Novel Computational Paradigm in Schizophrenia Based on Large Language Models
%A Nenchev, Ivan
%A Montag, Christiane
%A Just, Sandra Anna
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F nenchev-etal-2025-reverse
%X 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 \ensuremath< .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.
%U https://aclanthology.org/2025.ranlp-1.92/
%P 797-806
Markdown (Informal)
[Reverse Prompting: A Novel Computational Paradigm in Schizophrenia Based on Large Language Models](https://aclanthology.org/2025.ranlp-1.92/) (Nenchev et al., RANLP 2025)
ACL