EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910204984033280 |
|---|---|
| author | Guo, Pengze Liang, Jingxi Xie, Zhiwen Wang, Qifeng Wong, Derek F. |
| author_facet | Guo, Pengze Liang, Jingxi Xie, Zhiwen Wang, Qifeng Wong, Derek F. |
| contents | In the context of today's high-pressure, aging society, the demand for large-scale emotional models capable of providing empathetic support is more critical than ever. However, existing benchmarks fail to simultaneously achieve ecological validity, signal clarity, and reliable fine-grained labeling. We introduce EmoS, a high-fidelity bilingual benchmark designed to resolve the limitations of ecological validity and noise in existing datasets by combining strictly filtered static slices with a dynamic Streaming Monologue subset. Supported by a rigorous dual-layer human annotation pipeline, EmoS provides trusted ground truth that captures continuous emotional evolution. Empirical results show that fine-tuning MLLMs (multimodal large language models) on EmoS yields significant gains over zero-shot baselines, laying the foundation for the training and evaluation of future emotion recognition models and empathy models. The dataset and code are publicly available at https://github.com/NLP2CT/EmoS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08847 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding Guo, Pengze Liang, Jingxi Xie, Zhiwen Wang, Qifeng Wong, Derek F. Computation and Language I.2.7 In the context of today's high-pressure, aging society, the demand for large-scale emotional models capable of providing empathetic support is more critical than ever. However, existing benchmarks fail to simultaneously achieve ecological validity, signal clarity, and reliable fine-grained labeling. We introduce EmoS, a high-fidelity bilingual benchmark designed to resolve the limitations of ecological validity and noise in existing datasets by combining strictly filtered static slices with a dynamic Streaming Monologue subset. Supported by a rigorous dual-layer human annotation pipeline, EmoS provides trusted ground truth that captures continuous emotional evolution. Empirical results show that fine-tuning MLLMs (multimodal large language models) on EmoS yields significant gains over zero-shot baselines, laying the foundation for the training and evaluation of future emotion recognition models and empathy models. The dataset and code are publicly available at https://github.com/NLP2CT/EmoS. |
| title | EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding |
| topic | Computation and Language I.2.7 |
| url | https://arxiv.org/abs/2605.08847 |