analiza aiqbench
This research introduces SIEVE, an agentic framework that decouples evidence acquisition from verification to efficiently detect misinformation in multimodal videos by focusing only on sparse, decision-relevant clues. By training a specialized agent with reinforcement learning to construct compact evidence packages, the approach reduces computational redundancy while enhancing transparency through explicit inspection trails. The method demonstrates superior performance over holistic baselines, offering a scalable solution for verifying complex video content without processing unnecessary data.
Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection
arXiv:2607.18080v1 Announce Type: cross Abstract: 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.
Abstract: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.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2607.18080 [cs.CV]
(or arXiv:2607.18080v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.18080 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 302 cuvinte
Subiecte conexe
Online Video Agent Harness for Long Video Understanding
arXiv · 14 sept. 2026
Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning
arXiv · 6 oct. 2026
Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
arXiv · 25 aug. 2026
[AINews] High Taste Testers Ep. 1
Latent Space · 17 oct. 2026