arXiv Computation and Language September 3, 2026 By Max Nelson, Hanoz Bhathena, Aviral Joshi, Saket Sharma

Incremental Pooled LLM Evaluation for Cost-Effective Retrieval Model Selection

Read the original on arXiv Computation and Language →

The paper proposes an incremental pooled LLM evaluation method for selecting retrieval models in production Retrieval-Augmented Generation (RAG) systems. By having a language model judge the union of documents retrieved by current candidates and expanding the pool only with new documents from added systems, the approach reuses judgments across all systems. Experiments on four benchmarks and a financial news QA deployment show strong correlation with gold-standard rankings, high preservation of pairwise orderings, and significant cost savings—up to 4.9× lower evaluation cost and 65–80% judgment reuse.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jul 1

RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora

arXiv:2604. 19047v2 Announce Type: replace-cross Abstract: Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity.

By Hanjun Cho, Jay-Yoon Lee

llms rag benchmarks

arXiv Machine Learning

Sep 10

Diagnosing LLM Reranker Behavior Under Fixed Evidence Pools

arXiv:2602.18613v2 Announce Type: replace Abstract: Standard reranking evaluations study how a reranker orders candidates returned by an upstream retriever. This setup couples ranking behavior with r...

By Baris Arat, Emre Sefer

llms rag

Hugging Face Trending Papers

Sep 8

Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems

Q2D-Web is a new large‑scale benchmark for agentic Retrieval‑Augmented Generation (RAG) systems, featuring a 190 million‑document web corpus and 70 k machine‑reformulated search queries in ten languages. It supplies three sets of relevance judgments—agent citations, production rankings, and a combined set enriched with LLM‑based labels—to evaluate first‑stage retrievers. Experiments on 13 retrievers show consistent ranking across judgment sets but significant variation across domains, languages, and query types, and demonstrate that a carefully sampled sub‑corpus can approximate full‑corpus evaluation with minimal loss in Recall@1000.

llms rag agents benchmarks

arXiv AI

Jun 30

Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off

arXiv:2603. 26815v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems for financial document QA typically follow a chunk-based paradigm: documents are split into fragments, embedded, and retrieved by similarity.

By Zhiyuan Cheng, Longying Lai, Yue Liu

llms rag agents benchmarks

arXiv Computation and Language

Aug 25

Robustness of IR Models to Collection Growth

The paper investigates how adding non‑relevant documents to a collection affects the performance of Information Retrieval (IR) models. It distinguishes between Multi‑Document‑Agnostic (MDA) models, which do not rely on other documents, and Multi‑Document‑Dependent (MDD) models, which do, and evaluates both on two collections with little topic overlap. Results show that all models suffer some performance loss when non‑relevant documents are added, but MDA models outperform MDD models in retrieval tasks, while both perform similarly in reranking.

By Emmanouil Georgios Lionis, Debasis Ganguly, Sean MacAvaney

arXiv Computation and Language

Aug 27

Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting

The paper introduces “PACE”, a training‑free framework that tackles bottlenecks in Retrieval‑Augmented Generation by frontloading evidence and adaptively budgeting reranking. It first reorders candidate documents based on marginal evidence coverage—prioritizing query‑relevant, complementary, and chain‑forming documents—providing a $(1-1/e)$ approximation guarantee. Then it dynamically adjusts the reranking budget according to the relative pressure of the reranker and the language model, improving evidence recall and reducing p95 latency in multi‑hop QA workloads.

By Weibin Cai, Reza Zafarani