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
- Linked via arxiv authorJunyu Xiong →
Hierarchical Evidence-Driven Reasoning for Long Document Understanding
- Linked via arxiv authorYonghui Wang →
Hierarchical Evidence-Driven Reasoning for Long Document Understanding
- Linked via arxiv authorRongjian Gu →
Hierarchical Evidence-Driven Reasoning for Long Document Understanding
- Linked via arxiv authorChenyu Liu →
Hierarchical Evidence-Driven Reasoning for Long Document Understanding
- Linked via arxiv authorBing Yin →
Hierarchical Evidence-Driven Reasoning for Long Document Understanding
- Linked via arxiv authorWengang Zhou →
Hierarchical Evidence-Driven Reasoning for Long Document Understanding
- Linked via arxiv authorHouqiang Li →
Hierarchical Evidence-Driven Reasoning for Long Document Understanding