Metraipolis › archive › dc_337e8bcee205

When Audio and Video Mislead: Evaluating Multimodal AI for Conversational Emotion Recognition — arXiv:2611.11987

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.11987
License (as archived)
CC0-1.0
Archived
2026-11-10T18:44:45.188Z
SHA-256 of the archived text
41928abe78066bcdd0edca2ffa1ff242cf0dea548c2c2aacce5f23d9ecadb609
Stable URL of this page
https://metraipolis.com/documento/dc_337e8bcee205

How to cite

When Audio and Video Mislead: Evaluating Multimodal AI for Conversational Emotion Recognition — arXiv:2611.11987 — arXiv (en), https://arxiv.org/abs/2611.11987 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_337e8bcee205 (Metraipolis archive dc_337e8bcee205, sha256 41928abe78066bcdd0edca2ffa1ff242cf0dea548c2c2aacce5f23d9ecadb609)
BibTeX
@misc{dc337e8bcee205,
  title = {When Audio and Video Mislead: Evaluating Multimodal AI for Conversational Emotion Recognition — arXiv:2611.11987},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.11987},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_337e8bcee205; sha256 41928abe78066bcdd0edca2ffa1ff242cf0dea548c2c2aacce5f23d9ecadb609},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11987. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal Emotion Recognition in Conversation (MERC) combines lexical, acoustic, visual and conversational cues, but accepting audio and video does not establish their effective or robust use. We audit off-the-shelf Omni models while holding the target transcript and prior textual context fixed and adding, removing or replacing target audio and video. In the primary evaluation of Qwen2.5-Omni-7B, Baichuan-Omni-1.5 and MiniCPM-o 2.6 on MELD and the full five-session six-class IEMOCAP set, T+A improves Accuracy in all six model-dataset pairs, with four gains significant after false discovery rate (FDR) correction. Across three source mappings, unrelated A/V (RandA/V) lowers Accuracy relative to Full in all 18 comparisons; all 18 remain significant under dialogue-cluster inference and BH-FDR correction, both on common-valid pairs and when invalid/OOM outcomes are treated as incorrect. Comparisons with modality-omission baselines further distinguish replacement penalties from mismatch-specific harm. A Qwen/MELD case study finds significantly greater gold-vs-best-candidate margin recovery in Late than Early or Middle under decision-query audio knockout, relative to an edge-count-matched Video-Sham control, using Holm-corrected tests. These results distinguish genuine-modality benefit from sensitivity and vulnerability to misleading input.

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/2611.11987 — 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 2026-11-10T18:37:52.447Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).