AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMS with Audio-visual Cues
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917543575289856 |
|---|---|
| author | Zhou, Dingkun Patel, Krish Kankipati, Ajay Gupta, Akshaj Li, Zeyi Austin Shukla, Mohul Narang, Vibhor Kofman, Sara Ye, Zongli Wang, Grace Shi, Xiaoyu Li, Tingle Lin, Guan-Ting Cheng, Kan Jen Chou, Huang-Cheng Lian, Jiachen Anumanchipalli, Gopala |
| author_facet | Zhou, Dingkun Patel, Krish Kankipati, Ajay Gupta, Akshaj Li, Zeyi Austin Shukla, Mohul Narang, Vibhor Kofman, Sara Ye, Zongli Wang, Grace Shi, Xiaoyu Li, Tingle Lin, Guan-Ting Cheng, Kan Jen Chou, Huang-Cheng Lian, Jiachen Anumanchipalli, Gopala |
| contents | Emotions conveyed through voice and face shape engagement and context in human AI interaction. Despite rapid progress in omni modal large language models, the holistic evaluation of emotional reasoning with audiovisual cues remains limited. To address this gap, we introduce AV EMO Reasoning, a benchmark designed to systematically assess emotional reasoning abilities in large language models. The framework uses a curated audiovisual corpus comprising synthetic single turn and multi turn dialogues and a real world subset, together with emotion perception and interaction reasoning metrics, to evaluate whether models can understand user emotions and produce appropriate responses. By releasing a systematic evaluation benchmark, AV EMO Reasoning offers a reproducible standard for evaluating emotion aware dialogue and advances toward more natural, adaptive human AI interaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07355 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMS with Audio-visual Cues Zhou, Dingkun Patel, Krish Kankipati, Ajay Gupta, Akshaj Li, Zeyi Austin Shukla, Mohul Narang, Vibhor Kofman, Sara Ye, Zongli Wang, Grace Shi, Xiaoyu Li, Tingle Lin, Guan-Ting Cheng, Kan Jen Chou, Huang-Cheng Lian, Jiachen Anumanchipalli, Gopala Multimedia Sound Emotions conveyed through voice and face shape engagement and context in human AI interaction. Despite rapid progress in omni modal large language models, the holistic evaluation of emotional reasoning with audiovisual cues remains limited. To address this gap, we introduce AV EMO Reasoning, a benchmark designed to systematically assess emotional reasoning abilities in large language models. The framework uses a curated audiovisual corpus comprising synthetic single turn and multi turn dialogues and a real world subset, together with emotion perception and interaction reasoning metrics, to evaluate whether models can understand user emotions and produce appropriate responses. By releasing a systematic evaluation benchmark, AV EMO Reasoning offers a reproducible standard for evaluating emotion aware dialogue and advances toward more natural, adaptive human AI interaction. |
| title | AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMS with Audio-visual Cues |
| topic | Multimedia Sound |
| url | https://arxiv.org/abs/2510.07355 |