Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection
📰 ArXiv cs.AI
Researchers propose a framework combining LLMs with Multiple-Instance Learning to detect cognitive distortions with improved interpretability and reasoning
Action Steps
- Decompose utterances into Emotion, Logic, and Behavior components
- Apply Multiple-Instance Learning architecture to handle contextual ambiguity
- Integrate Large Language Models to enhance expression-level reasoning and interpretability
- Evaluate the framework's performance on cognitive distortion detection tasks
Who Needs to Know This
This research benefits AI engineers and ML researchers working on natural language processing and cognitive distortion detection, as it provides a novel approach to addressing contextual ambiguity and semantic overlap
Key Insight
💡 Combining LLMs with MIL architecture can improve interpretability and reasoning in cognitive distortion detection
Share This
💡 Detecting cognitive distortions with LLMs and Multiple-Instance Learning! 🤖
Key Takeaways
Researchers propose a framework combining LLMs with Multiple-Instance Learning to detect cognitive distortions with improved interpretability and reasoning
Full Article
Title: Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection
Abstract:
arXiv:2509.17292v2 Announce Type: replace-cross Abstract: Cognitive distortions have been closely linked to mental health disorders, yet their automatic detection remained challenging due to contextual ambiguity, co-occurrence, and semantic overlap. We proposed a novel framework that combines Large Language Models (LLMs) with Multiple-Instance Learning (MIL) architecture to enhance interpretability and expression-level reasoning. Each utterance was decomposed into Emotion, Logic, and Behavior (E
Abstract:
arXiv:2509.17292v2 Announce Type: replace-cross Abstract: Cognitive distortions have been closely linked to mental health disorders, yet their automatic detection remained challenging due to contextual ambiguity, co-occurrence, and semantic overlap. We proposed a novel framework that combines Large Language Models (LLMs) with Multiple-Instance Learning (MIL) architecture to enhance interpretability and expression-level reasoning. Each utterance was decomposed into Emotion, Logic, and Behavior (E
DeepCamp AI