Faegheh Hasibi

Multimodal RAG systems can now be more reliable: LeMUQ accurately quantifies uncertainty by modeling interactions between modalities and retrieved context, outperforming existing UQ methods.

Neural retrievers, despite their success on standard benchmarks, fail spectacularly when forced to reason about set-theoretic constraints, revealing a reliance on spurious correlations rather than true compositional understanding.

Current benchmarks fail to rigorously evaluate deep research agents, but a new framework leveraging structured knowledge bases and synthetic data offers a verifiable and scalable solution.