paper-with-me

Papers

Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?

2026-06-14 · Sadanand Singh, Allam Reddy, Manan Chopra arxiv

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. The benefits reported for these methods come almost exclusively from homogeneous corpora, predominantly Wikipedia prose. Whether they hold on the mixed-format collections common in practice, where code, markdown, tables, scientific PDFs, and prose are interleaved within one corpus, has not been measured. To study this directly, we build \textbf{HetDocQA}, a heterogeneous benchmark with \emph{chunker-agnostic} span-overlap relevance labels and collection-disjoint splits, and pair it with MuSiQue and QASPER as homogeneous controls. We evaluate eight methods on a shared backbone, with bootstrap confidence intervals and multiple-comparison correction. A strong cross-encoder reranker accounts for most of the pipeline's quality; beyond it, only two methods yield reliable gains: query expansion and SSCC. SSCC, a per-source calibrated corrector introduced here, sets a separate acceptance threshold for each score source and helps only on heterogeneous data. The remaining reranking and pool-expansion methods in common use, among them hierarchical summarization, graph expansion, routing, and rank fusion, give no reliable gain once that reranker is present.

📄 PDF Abstract BibTeX arXiv:2606.28367

Code (0)

등록된 구현이 없습니다.

Tasks

Document Summarization

Similar Papers 제목 키워드 기반

Drowning in Documents: Consequences of Scaling Reranker Inference

2024-11-18 · Mathew Jacob, Erik Lindgren, Matei Zaharia, Michael Carbin 외

Rerankers, typically cross-encoders, are often used to re-score the documents retrieved by cheaper initial IR systems. This is because, though expensive, rerankers are assumed to be more effective. We challenge this assu…

RerankingRetrieval

eXplainable Bayesian Multi-Perspective Generative Retrieval

2024-02-04 · EuiYul Song, Philhoon Oh, Sangryul Kim, James Thorne

Modern deterministic retrieval pipelines prioritize achieving state-of-the-art performance but often lack interpretability in decision-making. These models face challenges in assessing uncertainty, leading to overconfide…

Decision MakingFact CheckingQuestion AnsweringReranking+1

Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval

2025-09-08 · Haike Xu, Tong Chen arxiv

The widely used retrieve-and-rerank pipeline faces two critical limitations: they are constrained by the initial retrieval quality of the top-k documents, and the growing computational demands of LLM-based rerankers rest…

Guiding Retrieval using LLM-based Listwise Rankers

2025-01-15 · Mandeep Rathee, Sean MacAvaney, Avishek Anand

Large Language Models (LLMs) have shown strong promise as rerankers, especially in ``listwise'' settings where an LLM is prompted to rerank several search results at once. However, this ``cascading'' retrieve-and-rerank …

Retrieval

Beyond Retrieval: A Multitask Benchmark and Model for Code Search

2026-05-06 · Siqiao Xue, Zihan Liao, Jin Qin, Ziyin Zhang 외 arxiv

Code search has usually been evaluated as first-stage retrieval, even though production systems rely on broader pipelines with reranking and developer-style queries. Existing benchmarks also suffer from data contaminatio…

Code Search