BERAG applies Bayesian ensemble weighting of individual documents via token-by-token posterior updates in retrieval-augmented generation, yielding gains on knowledge-based visual QA tasks.
InProceedings of the 2024 Conference on Empirical Methods in Natural Lan- guage Processing, Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (Eds.)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Document-as-image representations underperform text-based and interleaved multimodal approaches for scientific document retrieval on a new LaTeX-derived benchmark.
ColChunk adaptively chunks visual document patches into contextual multi-vectors via clustering, cutting storage by over 90% while raising average nDCG@5 by 9 points.
citing papers explorer
-
BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering
BERAG applies Bayesian ensemble weighting of individual documents via token-by-token posterior updates in retrieval-augmented generation, yielding gains on knowledge-based visual QA tasks.
-
Document-as-Image Representations Fall Short for Scientific Retrieval
Document-as-image representations underperform text-based and interleaved multimodal approaches for scientific document retrieval on a new LaTeX-derived benchmark.
-
Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
ColChunk adaptively chunks visual document patches into contextual multi-vectors via clustering, cutting storage by over 90% while raising average nDCG@5 by 9 points.