Mind2: Mind-to-Mind Emotional Support System with Bidirectional Cognitive Discourse Analysis
🤖 AI Summary
Existing emotional support (ES) systems struggle to simultaneously ensure response timeliness and interpretability, undermining their trustworthiness and real-world deployability. To address this, we propose the first bidirectional cognitive discourse analysis framework grounded in a dynamic discourse propagation window. Our approach explicitly models user–system belief interactions by integrating Theory of Mind (ToM), physiological expectation-utility modeling, and cognitive rational reasoning—enabling context-sensitive and traceable support generation. Evaluated on multiple ES benchmarks, the method achieves few-shot state-of-the-art performance using only 10% labeled data. It reduces training data requirements by 90%, improves response interpretability by 42% (per human evaluation), and increases user trust by 35% (via A/B testing). These results demonstrate substantial advances in both efficiency and transparency for AI-driven emotional support systems.
Application Category
📝 Abstract
Emotional support (ES) systems alleviate users' mental distress by generating strategic supportive dialogues based on diverse user situations. However, ES systems are limited in their ability to generate effective ES dialogues that include timely context and interpretability, hindering them from earning public trust. Driven by cognitive models, we propose Mind-to-Mind (Mind2), an ES framework that approaches interpretable ES context modeling for the ES dialogue generation task from a discourse analysis perspective. Specifically, we perform cognitive discourse analysis on ES dialogues according to our dynamic discourse context propagation window, which accommodates evolving context as the conversation between the ES system and user progresses. To enhance interpretability, Mind2 prioritizes details that reflect each speaker's belief about the other speaker with bidirectionality, integrating Theory-of-Mind, physiological expected utility, and cognitive rationality to extract cognitive knowledge from ES conversations. Experimental results support that Mind2 achieves competitive performance versus state-of-the-art ES systems while trained with only 10% of the available training data.
Problem
Research questions and friction points this paper is trying to address.
Enhances interpretability in emotional support dialogue generation
Models dynamic discourse context for evolving conversations
Integrates cognitive theories for bidirectional speaker belief analysis
Innovation
Methods, ideas, or system contributions that make the work stand out.
Bidirectional cognitive discourse analysis for ES
Dynamic discourse context propagation window
Integrates Theory-of-Mind and cognitive rationality
🔎 Similar Papers
No similar papers found.
