arXiv AI

ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation

The paper introduces ORDER, a task‑conditioned retrieval‑augmented generation framework that dynamically adapts both indexing and retrieval strategies to each incoming query. It first clusters questions to learn cluster‑specific chunking, metadata filtering, and reranking settings, then routes queries to the appropriate pre‑built index via nearest‑centroid assignment. Additionally, a supervised query router predicts relevant collections and a Uniform Multi‑source Sampler distributes the retrieval budget evenly across selected sources, yielding superior performance on heterogeneous historical archives compared to existing RAG systems.

arXiv AI
1d ago

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.

By Neeraj Anand, Payel Santra, Partha Basuchowdhuri, Debasis Ganguly, Sumit Bhatia
arXiv Computation and Language
Aug 25

W-RAG: Source-Aware Retrieval for Enterprise Document Generation from Heterogeneous Knowledge Bases

W-RAG is a source-aware retrieval framework designed for enterprise document generation from heterogeneous knowledge bases. It uses ontology-guided retrieval, local ranking within each knowledge base, and source-level weighting to balance evidence from diverse sources. A new dataset covering multiple document types and industry domains demonstrates that W-RAG improves document coverage and generation quality compared to standard RAG pipelines.

By Hridya Dhulipala, Rajesh Ombase, Michael Wang, Tien N. Nguyen
Hugging Face Trending Papers
Aug 17

LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents

LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent. Existing retrieval-augmented approaches pre-materialize evidence via fixed chunking, embeddings, or persistent indexes: effective for lookup, yet costly, stale-prone, and committed to a granularity before the query is known.

arXiv Machine Learning
Sep 11

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

VikingRAG is a directory‑aware semantic data management system that reduces token usage in retrieval‑augmented generation by tightly integrating semantic and structural access. It employs multi‑round retrieval traces as reusable experience edges and an adaptive escalation strategy to avoid unnecessary multi‑round exploration. Experiments show that VikingRAG achieves comparable accuracy to state‑of‑the‑art methods while using only 11.6%–51.9% of their tokens, and further reductions to 5.1%–32.5% with trace reuse and escalation.

By Peiyuan Gao, Gaoyuan Zhang, Haojie Qin, Yahui Sun, Qianyi Zhang, Yunhao Zhang, Zeyu Wang, Wei Lu
arXiv Machine Learning
Sep 11

REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving

The paper introduces REVA, a method for compressing retrieval-augmented generation (RAG) prompts by aggregating historical query–document–model interactions into reusable evidence views. REVA mines attention traces from the target generator, maps token-level attention to readable words, aggregates importance across repeated document accesses, and produces budget‑specific plain‑text views that maintain document order and the standard RAG interface. Experiments on four benchmarks with modern LLMs show that REVA improves generation quality by 1.0–5.8 points over existing compressors while reducing compression overhead by 5.3 to 15.6 times and adding less than 40 ms of latency.

By Tuan Nguyen, Qiran Hu, Banruo Liu, Khoa D. Doan, Kok-Seng Wong, Fan Lai