EG-VQA: 基于接地时间证据的可验证视频问答基准
EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence
AI总结：
提出EG-VQA基准，通过细粒度时间证据标注和EG-F1指标，揭示视频大模型在答案正确性与证据定位之间的差距，并引入EG-Reasoner模型弥合这一差距。
摘要：
近期视频大语言模型（Video-LLMs）的进展在视频问答（VideoQA）上取得了有前景的性能。然而，现有基准主要通过答案正确性进行评估，而预测结果在相关视频证据中的定位在很大程度上仍未得到检验。答案生成与证据理解之间的脱节促使我们构建了证据接地视频问答基准（EG-VQA），这是一个开放式评估协议，其中每个问答对都明确标注了支持性时间证据，从而要求联合推理和精确证据定位。EG-VQA包含2,067个视频和11,838个问答对，带有细粒度证据标注。为了评估预测证据，引入了证据接地F1（EG-F1）作为统一指标，该指标联合衡量与真实证据的时间对齐和语义一致性。实验评估显示，即使是强大的专有模型也难以准确定位其预测，揭示了答案正确性与忠实证据定位之间的根本差距。为弥合这一差距，提出了EG-Reasoner，一种通过显式监督训练的证据接地推理模型。在开源模型中取得了最先进的性能，结果与专有系统具有竞争力，特别是在反事实问题等推理密集型任务上观察到显著提升。这些发现表明，仅靠扩展不足以实现稳健的视频理解，结构化证据监督对于开发更可靠和可解释的VideoQA系统至关重要。
英文摘要：
Recent advances in Video Large Language Models (Video-LLMs) have yielded promising performance on Video Question Answering (VideoQA). Nevertheless, existing benchmarks are predominantly evaluated through answer correctness, while the faithfulness of predicted evidence supporting those answers remains insufficiently evaluated. This disconnect between answer generation and evidence verification motivates the construction of the Evidence-Grounded Video Question Answering Benchmark (EG-VQA), a large-scale open-ended benchmark in which each QA pair is annotated with temporally localized textual evidence, requiring models to jointly produce answers and verifiable evidence. EG-VQA comprises 2,067 videos and 11,838 QA pairs with fine-grained evidence annotations. To evaluate predicted evidence, Evidence-Grounded F1 (EG-F1) is introduced as a metric that jointly measures temporal alignment and semantic consistency between predicted and ground-truth evidence. Experiments reveal a substantial discrepancy between answer correctness and evidence faithfulness: even strong proprietary models can achieve high answer accuracy while exhibiting gaps in temporal-semantic grounding. To investigate evidence-aware learning under EG-VQA, we develop EG-Reasoner, an evidence-aware model trained with explicit evidence supervision. EG-Reasoner achieves strong evidence grounding performance among open-source models while maintaining competitive answer generation results compared with proprietary systems. These findings highlight the importance of explicitly modeling evidence grounding and suggest that evidence-aware supervision provides an effective direction toward more reliable and interpretable VideoQA systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
