EviProp improves evidence-page retrieval in long multimodal documents by combining dense visual priors with sparse chunk seeds and running Personalized PageRank on a multimodal Chunk-Page graph.
Hirag: Hierarchical-thought instruction-tuning retrieval-augmented generation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.IR 3verdicts
UNVERDICTED 3representative citing papers
SemFlowRAG reconstructs retrieval graphs into directed semantic flows from high to low abstractness via embedding-variance measures and modified PageRank to reduce probability black holes and improve complex QA performance.
GroupRank uses groupwise LLM reranking with answer-free data synthesis and a group-ranking reward to reach 65.2 NDCG@10 on BRIGHT while providing 6.4x faster inference than listwise baselines.
citing papers explorer
-
EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval
EviProp improves evidence-page retrieval in long multimodal documents by combining dense visual priors with sparse chunk seeds and running Personalized PageRank on a multimodal Chunk-Page graph.
-
SemFlowRAG: Directed Semantic Flow from Abstraction to Evidence for Complex Reasoning
SemFlowRAG reconstructs retrieval graphs into directed semantic flows from high to low abstractness via embedding-variance measures and modified PageRank to reduce probability black holes and improve complex QA performance.
-
GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs
GroupRank uses groupwise LLM reranking with answer-free data synthesis and a group-ranking reward to reach 65.2 NDCG@10 on BRIGHT while providing 6.4x faster inference than listwise baselines.