Metraipolis › archive › dc_e16abb028996
Rationale-Guided Learning for Multimodal Emotion Recognition — arXiv:2608.10448
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10448
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:08:23.317Z
- SHA-256 of the archived text
eb648937a25a307a186b45545d96ec216ae8fb9a84a26c6e346c9cf11ab88ca6- Stable URL of this page
https://metraipolis.com/documento/dc_e16abb028996
How to cite
Rationale-Guided Learning for Multimodal Emotion Recognition — arXiv:2608.10448 — arXiv (en), https://arxiv.org/abs/2608.10448 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e16abb028996 (Metraipolis archive dc_e16abb028996, sha256 eb648937a25a307a186b45545d96ec216ae8fb9a84a26c6e346c9cf11ab88ca6)
BibTeX
@misc{dce16abb028996,
title = {Rationale-Guided Learning for Multimodal Emotion Recognition — arXiv:2608.10448},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10448},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e16abb028996; sha256 eb648937a25a307a186b45545d96ec216ae8fb9a84a26c6e346c9cf11ab88ca6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10448. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal emotion recognition in conversation (MERC) requires understanding complex interactions between verbal and non-verbal cues. However, most existing approaches fundamentally treat this as a direct input-output (multimodal cues-emotion labels) mapping problem, overlooking the causal reasoning that humans use when interpreting emotions. We propose rationale-guided learning (RGL), a novel framework that transforms MERC into a cognitively-inspired reasoning task. Based on dual-process theory, we decompose emotional reasoning into three facets: Intuitive (immediate perception, System 1), Contextual (situational analysis, System 2), and Integrative (synthesis of both). We leverage an MLLM offline to generate structured rationales, which are encoded as memories to guide model training via aligning internal representations with human-like reasoning patterns. Our final model operates without any MLLM overheads at inference time. Experimental results show that RGL achieves state-of-the-art performance on the IEMOCAP and MELD benchmarks. Further, for interpretation, we demonstrate that the model's internal features effectively retrieve semantically correct rationales for unseen test samples, validating its rationale reasoning capabilities. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.10448 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T05:57:28.268Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).