Two of our papers were accepted at EMNLP 2026

The two papers study whether language models explain emotions for the right structural reasons and how psychologically grounded cognitive projections can improve retrieval-augmented conversational mental health support.

• Hajime Hotta and Minh-Tien Nguyen, “Right for the Right Reasons? Evaluating the Structural Fidelity of LLM Emotion Explanations,” in Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026 (accepted).

• Minh-Tien Nguyen, Huu-Loi Le, Manh-Cuong Phan, Duong-Hieu Le, Dinh-Phuc Pham, Van-Quyet Nguyen, and Hajime Hotta, “Reframe to Retrieve: Cognition-aware RAG with Projections Inspired by Appraisal and CBT for Conversational Mental Health Support,” in Findings of the Association for Computational Linguistics: EMNLP 2026 (accepted).