arXiv Computation and Language
RAGCompass: Generalizable Retriever Routing via Reranking
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Computation and Language
Sep 15
Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers
arXiv:2609.13486v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning decoder-only large language models (LLMs) for retrieval yields strong first-stage retrievers, with effectivene...
arXiv Machine Learning
Sep 14
Beyond the Query: Do Retrieval Signals Improve Adaptive Multimodal RAG Routing?
The paper investigates whether retrieval-time signals add value to Adaptive Retrieval-Augmented Generation (RAG) routing when the query is already known. Experiments across document, audio, and video RAG compare routers that use only the query versus those that also incorporate retrieval signals, keeping all other factors constant. The results show that adding retrieval signals does not reliably improve routing decisions over a query-only baseline, suggesting that any routing benefit must be explicitly demonstrated rather than presumed.
Hugging Face Trending Papers
Oct 26
Retriever-Free Retrieval: Navigating Documents with Decision Models
While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the r...
arXiv AI
Oct 27
Retriever-Free Retrieval: Navigating Documents with Decision Models
arXiv:2610.35868v1 Announce Type: new Abstract: While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces...
Hugging Face Trending Papers
Aug 16
Dense Expands, Sparse Anchors: Channel-Asymmetric Query Expansion for Hybrid Retrieval
LLM-based query expansion improves retrieval by generating document-like passages. In hybrid retrieval, however, most evaluations fuse fixed top-$L$ dense and sparse rankings. Because the cutoff contr...
arXiv AI
Sep 17
One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAG
The paper introduces DRAG, a query‑adaptive framework that jointly selects retriever and generator configurations for Retrieval‑Augmented Generation (RAG) systems. Two variants are presented: DRAG_QPP, a training‑free routing method using Query Performance Prediction and perplexity signals, and DRAG_SFT, a supervised approach that fine‑tunes an LLM to predict configurations. Experiments on three LLM families and four QA benchmarks show that DRAG_QPP matches strong static baselines while cutting inference latency, and DRAG_SFT consistently outperforms both static and training‑free adaptive baselines, demonstrating a better effectiveness‑efficiency trade‑off.