arXiv AI
DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 30
Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?
arXiv:2606. 28367v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval.
arXiv Computation and Language
Sep 1
Query Expansion Should Be Coordinated: Dense Expands, Sparse Anchors
arXiv:2608.15851v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) systems rely on retrieval modules to ground large language model (LLM) outputs. LLM-based query expansio...
arXiv Computation and Language
Oct 12
Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking
Lychee‑Reranker is a fast, not‑late‑interaction reranker that decouples query and passage computation while preserving expressive relevance modeling. It uses an encoder–decoder architecture: passages are pre‑encoded with Matryoshka embedding pooling, and the decoder jointly processes system/user instructions and query intent, with cross‑attention capturing fine‑grained relevance. The design yields four benefits—offline passage encoding for efficiency, cross‑attention expressiveness, compact Matryoshka pooling, and adjustable test‑time compute—and is available in Nano, Small, and Large sizes (0.27B, 1B, and 4B activated parameters).
Hugging Face Trending Papers
Jun 22
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
As retrieval systems scale, high-quality reranking becomes increasingly important. However, most existing rerankers, whether encoder-based or decoder-based, jointly encode the query and passage, tightly coupling their computation and limiting deployment efficiency as well as flexibility.
arXiv Computation and Language
5d ago
SAG2: Embedding-Free Multi-Hop Retrieval with BM25 and JEV
SAG2 is an embedding‑free multi‑hop retrieval system that relies on a single SQLite database, BM25, and contextual evidence decisions from JEV. It replaces dense indexes with a lexical index over original passages, allowing query‑time evidence selection without offline embedding computation or dedicated database servers. On several benchmark datasets, SAG2 achieves the highest Recall@5 and Recall@10, demonstrating strong retrieval accuracy with lightweight preparation and rapid indexing.
arXiv AI
Aug 18
What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering
arXiv:2608. 14841v1 Announce Type: new Abstract: Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines.