Hierarchical Evidence-Driven Reasoning for Long Document Understanding
Retrieval-Augmented Generation (RAG) streamlines long-document understanding by leveraging retrieval mechanisms to restrict input images to a highly curated subset. However, existing multimodal RAG pipelines primarily face two critical challenges: first, standard semantic similarity retrievers frequently fetch topically overlapping yet answer-void distractor pages that mislead downstream generation; second, rigid single-pass pipelines heavily depend on initial retrieval success, where any omission of core evidence inevitably causes cascading errors. To address these challenges, we introduce HI
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 48%NirDiamant/RAG_Techniques →
- LinkedLinked via arxiv author · 85%Junyu Xiong →
“Hierarchical Evidence-Driven Reasoning for Long Document Understanding”
- LinkedLinked via arxiv author · 85%Yonghui Wang →
“Hierarchical Evidence-Driven Reasoning for Long Document Understanding”
- LinkedLinked via arxiv author · 85%Rongjian Gu →
“Hierarchical Evidence-Driven Reasoning for Long Document Understanding”
- LinkedLinked via arxiv author · 85%Chenyu Liu →
“Hierarchical Evidence-Driven Reasoning for Long Document Understanding”
- LinkedLinked via arxiv author · 85%Bing Yin →
“Hierarchical Evidence-Driven Reasoning for Long Document Understanding”
- LinkedLinked via arxiv author · 85%Wengang Zhou →
“Hierarchical Evidence-Driven Reasoning for Long Document Understanding”
- LinkedLinked via arxiv author · 85%Houqiang Li →
“Hierarchical Evidence-Driven Reasoning for Long Document Understanding”