# Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection

arXiv: https://arxiv.org/abs/2509.17292 · HTML: https://mlsanity.com/paper/2509.17292/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 5 of its 41 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 5 of 5)

- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers](https://mlsanity.com/paper/2012.15828/) (2020)
- [Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Prompting](https://mlsanity.com/paper/2310.07146/) (2023)
- [KoACD: The First Korean Adolescent Dataset for Cognitive Distortion Analysis via Role-Switching Multi-LLM Negotiation](https://mlsanity.com/paper/2505.00367/) (2025)
- [Deep Multi-Instance Transfer Learning](https://mlsanity.com/paper/1411.3128/) (2014)

## Built on by (most cited first, 1 of 1)

- [Multi-Perspective Triad Interaction Graph Neural Network for Cognitive Distortion Detection](https://mlsanity.com/paper/2608.06785/) (2026)

## Abstract (arXiv)

Cognitive distortions have been closely linked to mental health disorders, yet their automatic detection remains challenging due to contextual ambiguity, co-occurrence, and semantic overlap. We propose a novel framework that combines Large Language Models (LLMs) with a Multiple-Instance Learning (MIL) architecture to enhance interpretability and expression-level reasoning. Each utterance is decomposed into Emotion, Logic, and Behavior (ELB) components, which are processed by LLMs to infer multiple distortion instances, each with a predicted type, expression, and model-assigned salience score. These instances are integrated via a Multi-View Gated Attention mechanism for final classification. Experiments on Korean (KoACD) and English (Therapist QA) datasets demonstrate that incorporating ELB and LLM-inferred salience scores improves classification performance, especially for distortions with high interpretive ambiguity. Our results suggest a psychologically grounded and generalizable approach for fine-grained reasoning in mental health NLP. The dataset and implementation details are publicly accessible.