Metraipolis › archive › dc_ed7ac34e09d7
FACES: Fine-grained Gated Semantic Alignment for Multimodal Emotional Support Conversation — arXiv:2610.20051
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20051
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:34:59.268Z
- SHA-256 of the archived text
de26f0f85e8f1cb51b10e4bba5ef8329b7d468388d8ebdf7f050b5ba5bd679e1- Stable URL of this page
https://metraipolis.com/documento/dc_ed7ac34e09d7
How to cite
FACES: Fine-grained Gated Semantic Alignment for Multimodal Emotional Support Conversation — arXiv:2610.20051 — arXiv (en), https://arxiv.org/abs/2610.20051 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed7ac34e09d7 (Metraipolis archive dc_ed7ac34e09d7, sha256 de26f0f85e8f1cb51b10e4bba5ef8329b7d468388d8ebdf7f050b5ba5bd679e1)
BibTeX
@misc{dced7ac34e09d7,
title = {FACES: Fine-grained Gated Semantic Alignment for Multimodal Emotional Support Conversation — arXiv:2610.20051},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20051},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed7ac34e09d7; sha256 de26f0f85e8f1cb51b10e4bba5ef8329b7d468388d8ebdf7f050b5ba5bd679e1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20051. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In recent years, with advances in multimodal interaction technologies and the growing demand for intelligent emotional support, Multimodal Emotional Support Conversation (MESC) has emerged as an important task. However, existing systems still suffer from shallow responses and inappropriate support strategies due to weak semantic feedback, cross-dimension reward compensation, and coarse reasoning supervision. To address these challenges, we propose FACES, a fine-grained gated semantic alignment framework for MESC. Specifically, FACES integrates multi-source rewards to construct multidimensional semantic and functional alignment signals, employs a non-compensatory gated fusion mechanism to reduce cross-dimension reward offset, and leverages structured Chain-of-Thought (CoT) anchors to perform token-level credit assignment. Under a controlled response-length protocol, FACES improves the average MLLM-based evaluation score from 3.61 to 4.04 and achieves an 80.22% pairwise win rate over SOTA. Human evaluation under the same protocol yields a 75.3% preference rate. Results on three external datasets further support transferability. The code and dataset are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.20051 — 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 2026-10-15T19:36:18.239Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).