POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913177250299904 |
|---|---|
| author | Dahal, Ashim Ghimire, Ankit Murad, Saydul Akbar Rahimi, Nick |
| author_facet | Dahal, Ashim Ghimire, Ankit Murad, Saydul Akbar Rahimi, Nick |
| contents | Long-video multimodal question answering requires structured reasoning over visual evidence and dialogue, but Large Vision-Language Models (LVLMs) are constrained by context-window and compute limits. We propose POVQA, which compresses each second into a temporally pooled image (1 fps pooled images) to maintain dense temporal coverage under a fixed token budget. We then train Qwen2.5-VL-7B with supervised fine-tuning (SFT) on rationale+answer targets, and optionally apply Direct Preference Optimization (DPO) for preference alignment. We introduce ReasonVQA as a pilot diagnostic dataset with 12 movies and 239 human-annotated QA+rationale triplets for controlled analysis of long-context multimodal reasoning under compression. On ReasonVQA, SFT improves the best pooled-only baseline from 0.212 to 0.550 F1, showing that pooled evidence plus rationale supervision provides the main performance gains in this setting. In zero-shot transfer, POVQA also reaches 64.7\% on TVQA after SFT+DPO. These results are preliminary: ReasonVQA is small, pooling can lose fine-grained temporal order, and DPO effects are not uniformly positive across settings. Code, dataset, and additional qualitative evaluations are available at \href{https://povqa.github.io}{https://povqa.github.io}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01009 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency Dahal, Ashim Ghimire, Ankit Murad, Saydul Akbar Rahimi, Nick Computer Vision and Pattern Recognition Multimedia Long-video multimodal question answering requires structured reasoning over visual evidence and dialogue, but Large Vision-Language Models (LVLMs) are constrained by context-window and compute limits. We propose POVQA, which compresses each second into a temporally pooled image (1 fps pooled images) to maintain dense temporal coverage under a fixed token budget. We then train Qwen2.5-VL-7B with supervised fine-tuning (SFT) on rationale+answer targets, and optionally apply Direct Preference Optimization (DPO) for preference alignment. We introduce ReasonVQA as a pilot diagnostic dataset with 12 movies and 239 human-annotated QA+rationale triplets for controlled analysis of long-context multimodal reasoning under compression. On ReasonVQA, SFT improves the best pooled-only baseline from 0.212 to 0.550 F1, showing that pooled evidence plus rationale supervision provides the main performance gains in this setting. In zero-shot transfer, POVQA also reaches 64.7\% on TVQA after SFT+DPO. These results are preliminary: ReasonVQA is small, pooling can lose fine-grained temporal order, and DPO effects are not uniformly positive across settings. Code, dataset, and additional qualitative evaluations are available at \href{https://povqa.github.io}{https://povqa.github.io}. |
| title | POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2510.01009 |