Back

Mapping OCD Symptom Triggers with Large Language Models

Bentz, D.; Wulff, D. U.

2025-05-16 psychiatry and clinical psychology
10.1101/2025.05.15.25327706 medRxiv
Show abstract

Recent advancements in natural language processing (NLP) and large language models (LLMs) offer new avenues for exploring previously under-researched areas in mental health. Their capacity to automatically and meaningfully analyze large-scale text data makes them particularly valuable for studying highly individualized phenomena with clinical relevance, such as triggers of obsessive-compulsive symptoms (OCS), where pattern identification is often challenging. To address this gap, we surveyed 1,495 individuals from the general population about contamination-related obsessive-compulsive symptoms (C-OCS), as well as their triggers and corresponding intensity. Using LLM-based embeddings, we generated a map of key trigger categories for C-OCS, revealing their diversity across ecological domains and varying degrees of semantic similarity. Monte Carlo simulations further showed that individuals frequently reported semantically similar trigger pairs that differed in intensity. These findings provide a basis for further investigations into associative learning processes at the categorial and semantic levels. Such research in turn may enhance understanding of mechanisms involved in the development, maintenance, and treatment of obsessive-compulsive disorders, and may inform novel therapeutic approaches.

Published in Communications Psychology · training set

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.