Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection
For the task of multimodal video misinformation detection, this work introduces a novel paradigm that improves efficiency and transparency by focusing on sparse evidence, though it is incremental in its application of agent-based methods to a known problem.
The paper proposes SIEVE, a framework for multimodal video misinformation detection that decouples evidence acquisition from verification, using an agent to seek sparse, decision-relevant clues. Experiments show SIEVE outperforms baselines on multiple benchmarks, enabling reliable verification with compact evidence packages.
Multimodal video misinformation detection is commonly formulated as a holistic video-understanding task, where the entire video and its associated content are processed and judged in a single pass. However, real-world misinformation often exhibits a sparse and compositional evidence structure: a reliable decision may depend on only a few coupled clues, while most video content contributes limited additional information. Exhaustive multimodal reasoning may therefore introduce substantial redundancy and obscure decisive evidence. This motivates decoupling evidence acquisition from verification: first identifying sparse, decision-relevant clues and then judging veracity based on the acquired evidence. Accordingly, we propose SIEVE, a framework for Sparse Interactive Evidence Verification via Extraction in multimodal video misinformation detection. An evidence-seeking agent actively explores the available multimodal evidence and constructs a compact evidence package, which is then used by a verifier to determine veracity. The agent is trained with supervised evidence-seeking trajectories and an evidence-aware reinforcement learning objective that promotes informative evidence acquisition while discouraging unnecessary or invalid interactions. Experiments on multiple video misinformation benchmarks show that SIEVE consistently outperforms the evaluated baselines and supports reliable verification using compact evidence packages. Moreover, the resulting acquisition process provides an explicit and inspectable evidence trail, improving the transparency and groundedness of multimodal misinformation detection.