Piecing It All Together: Verifying Multi-Hop Multimodal Claims
This addresses the problem of verifying complex multimodal claims for AI researchers, though it is incremental as it focuses on dataset creation rather than a novel method.
The authors tackled the lack of complex reasoning in claim verification by introducing a new task of multi-hop multimodal claim verification and creating MMCV, a dataset of 15k claims with multimodal evidence, which state-of-the-art models struggle with, especially as reasoning hops increase.
Existing claim verification datasets often do not require systems to perform complex reasoning or effectively interpret multimodal evidence. To address this, we introduce a new task: multi-hop multimodal claim verification. This task challenges models to reason over multiple pieces of evidence from diverse sources, including text, images, and tables, and determine whether the combined multimodal evidence supports or refutes a given claim. To study this task, we construct MMCV, a large-scale dataset comprising 15k multi-hop claims paired with multimodal evidence, generated and refined using large language models, with additional input from human feedback. We show that MMCV is challenging even for the latest state-of-the-art multimodal large language models, especially as the number of reasoning hops increases. Additionally, we establish a human performance benchmark on a subset of MMCV. We hope this dataset and its evaluation task will encourage future research in multimodal multi-hop claim verification.