How retriever redundancy and diversity impact RAG effectiveness

In RAG, while the retriever typically ranks documents by their individual relevance to the query, the generator instead produces an answer based on the retrieved documents as a whole. This paper investigates how redundancy and diversity from the retrieved document set impact the generator in terms of answer correctness. Previous work has provided a mix of findings: some showing that redundancy improves generation by reinforcing relevant information, others that LLM-based paraphrasing of the same content may be beneficial. Many of these studies did not control for confounding factors like whether the documents contained the exact answer or not, and if parametric knowledge plays a role. We conduct a carefully controlled experiment investigating three key scenarios of retrieved document sets: 1) Duplicate (exact copies of the same document), 2) Paraphrased (LLM rephrased versions of one document) and 3) Diverse (documents from different genres each containing relevant information in different forms). We control for which documents contain the answer in exact match or rephrased form. Evaluation is done with FictionalQA, a synthetic, fictional question-answer dataset that ensures the LLM generator prior knowledge cannot answer the question; the answer must come from retrieved documents. We show that duplicate redundancy and LLM paraphrasing does not significantly improve answer correctness. However, providing diverse documents is highly beneficial, improving answer correctness by 17%-47%. We further show this improvement is driven by diverse forms of document genre (news, blogs, etc.) alone and not a consequence of more relevant answer being available to generator. Our findings help to direct more attention to how new retrieval methods might improve RAG by catering to the generator preference for diversity in retrieval results.

Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Research Agents

Existing deep-research agents use a Search--Visit workflow that retrieves whole webpages without considering the structure they expose through titles, headings, sections, and metadata. This prevents agents from directly constraining retrieval to parts of a webpage and often carries irrelevant content into their context. We introduce \textsc{Sieve}, a search--inspect--fetch strategy driven by a Boolean Query Language (BQL): it searches webpage fields to filter candidates, uses an interchangeable ranker to order them, presents structure-rich result cards for inspection, and fetches only selected sections. Across three QA collections, \textsc{Sieve} is more accurate than the strongest conventional Search--Visit configuration on each collection while using $20.7$--$50.6\%$ fewer tokens. Boolean filtering improves every tested ranker, and the accuracy--context advantage persists across retriever choices and agent backbones. Our implementation is included in the SkimSearchAgent library at https://github.com/ielab/skim-search-agent.

Reproducing LightMem: Naive RAG Is Just as Good for Memory Management

Long-term conversational agents require access to information from earlier interactions, such as a user's preferences, past requests, or previously mentioned facts. Repeatedly providing the full dialogue history can be expensive as conversations grow, so many memory approaches instead transform past interactions into compact entries that can be retrieved when needed. LightMem is a recent lightweight memory-management approach that reports strong effectiveness while maintaining relatively low construction cost. However, it still relies on a separate constructed memory representation and is evaluated with only one retriever, leaving unclear how sensitive its results are to retriever choice and whether memory construction discards answer-relevant information. In this study, we reproduce LightMem and compare it with Naive RAG, which retrieves directly from raw user turns. We recover LightMem's main configuration trend, but find that retriever choice is a major source of performance variation: changing only the retriever over a fixed LightMem store shifts answer accuracy from 58.1% to 75.5%. Constructed memories also do not consistently outperform raw-turn retrieval. Naive RAG generally performs better at matched retrieval depths, whereas LightMem performs better mainly under tight answering-token budgets. Oracle evaluation further shows that memory construction removes some answer-relevant information. Overall, LightMem offers a context-efficiency trade-off rather than a general advantage over Naive RAG. Its value depends on the retriever and available token budget, motivating future work on retrieval, reranking, query formulation, and their interaction with raw and constructed memory representations.

Whole-Pool Setwise Reranking with Long-Context Language Models

Previous LLM-based passage re-rankers are often expensive and slow because the input context constraints require the LLM to make many dependent model calls. We study how recent long-context LLMs change this problem: when the full set of retrieved candidate passages can be shown to the model at once, ranking no longer has to be reconstructed from many overlapping local comparisons. We propose Whole-Pool Setwise re-ranking, where each call considers all currently unranked candidate passages, and introduce DualEnd, which identifies both the most and least relevant passages in one call. By filling the ranking from both ends, DualEnd ranks 100 candidates with 50 serial LLM calls, compared with 99 calls for comparable one-passage-at-a-time whole-pool methods. Experiments with nine open-weight LLMs on two passage re-ranking benchmarks, measuring effectiveness, call count, token use, runtime, and output reliability shows that long context is not merely more prompt space, but an opportunity to make LLM re-rankers both effective and efficient.

On the impact of retrieved content representations in RAG Pipelines

Retrieval-Augmented Generation (RAG) supplements a language model's input with retrieved documents, yet most RAG pipelines inherit retrieval components designed for human readers. How retrieved content should be represented when the consumer is a large language model (LLM) rather than a human is less well understood. Recent work has proposed transformations of retrieved content and identified properties that affect generation, but each examines a single transformation or property in isolation, leaving open which features of a document's representation matter most. We address this with a controlled comparison: holding retrieval fixed, we vary only the representation of retrieved documents, comparing an original baseline against thirteen transformations spanning selection, summarisation, and reformulation, in query-dependent and query-independent variants. Across these fourteen representations we measure question-answering accuracy for four generators, and for each representation we also measure answer retention: whether a known answer-bearing document still supports its answer after transformation. We find that answer retention is the primary determinant of generator accuracy; notably, when retention is high, a representation's wording, structure, length, and query-dependence have limited effect. This suggests that accuracy gains attributed to specific mechanisms in prior work may be partly explained by how well those mechanisms preserve answer-bearing content, an attribution that cannot be settled without controlling for retention.

Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings

Recent generative engine optimisation (GEO) research has shown that prompt-injection attacks can push a target product to the top of an LLM's recommendation list, with the strongest attacks reporting around $80\%$ success and raising serious security concerns about RAG-based recommendation. However, these results assume the attacked document is always fed directly to the generator, bypassing the retriever and reranker. This is unrealistic: in deployed RAG systems, the attack modifies the document content, which can in turn change whether the document is retrieved and reranked highly enough to reach the generator at all. In this paper, we re-evaluate seven GEO attacks under a realistic three-stage pipeline (retriever\,$\to$\,LLM reranker\,$\to$\,LLM generator). We find that prior protocols substantially overstate attack effectiveness: gradient-based and instruction override attacks largely collapse before reaching the generator, and only LLM-driven prompt injections remain effective end-to-end. Our analysis further reveals that current GEO attacks are easily detectable: a lightweight prompt-injection guard finetuned on a small attack dataset already detects every attack. Our code and data are available at https://github.com/ielab/geo_injection_rag_survival.

Toward Clinically Acceptable Chest X-ray Report Generation: A Qualitative Retrospective Pilot Study of CXRMate-2

Chest X-ray (CXR) radiology report generation (RRG) models have shown rapid progress, yet their clinical utility remains uncertain due to limited evaluation by radiologists. We present CXRMate-2, a state-of-the-art CXR RRG model that integrates structured multimodal conditioning and reinforcement learning with a composite reward for semantic alignment with radiologist reports. Across the MIMIC-CXR, CheXpert Plus, and ReXgradient datasets, CXRMate-2 achieves statistically significant improvements over strong benchmarks, including gains of 11.2% and 24.4% in GREEN and RadGraph-XL, respectively, on MIMIC-CXR relative to MedGemma 1.5 (4B). To directly compare CXRMate-2 against radiologist reporting, we conduct a blinded, randomised qualitative retrospective evaluation. Three consultant radiologists compare generated and radiologist reports across 120 studies from the MIMIC-CXR test set. Generated reports were deemed acceptable (defined as preferred or rated equally to radiologist reports) in 45% of ratings, with no statistically significant difference in preference rates between radiologist reports and acceptable generated reports for seven of the eight analysed findings. Preference for radiologist reports was driven primarily by higher recall, while generated reports were often preferred for readability. Together, these results suggest a credible pathway to clinically acceptable CXR RRG. Improvements in recall, alongside better detection of subtle findings (e.g., pulmonary congestion), are likely sufficient to achieve non-inferiority to radiologist reporting. With these targeted advances, CXR RRG systems may be ready for prospective evaluation in assistive roles within radiologist-led workflows.

Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval

Document chunking is a critical preprocessing step in dense retrieval systems, yet the design space of chunking strategies remains poorly understood. Recent research has proposed several concurrent approaches, including LLM-guided methods (e.g., DenseX and LumberChunker) and contextualized strategies(e.g., Late Chunking), which generate embeddings before segmentation to preserve contextual information. However, these methods emerged independently and were evaluated on benchmarks with minimal overlap, making direct comparisons difficult. This paper reproduces prior studies in document chunking and presents a systematic framework that unifies existing strategies along two key dimensions: (1) segmentation methods, including structure-based methods (fixed-size, sentence-based, and paragraph-based) as well as semantically-informed and LLM-guided methods; and (2) embedding paradigms, which determine the timing of chunking relative to embedding (pre-embedding chunking vs. contextualized chunking). Our reproduction evaluates these approaches in two distinct retrieval settings established in previous work: in-document retrieval (needle-in-a-haystack) and in-corpus retrieval (the standard information retrieval task). Our comprehensive evaluation reveals that optimal chunking strategies are task-dependent: simple structure-based methods outperform LLM-guided alternatives for in-corpus retrieval, while LumberChunker performs best for in-document retrieval. Contextualized chunking improves in-corpus effectiveness but degrades in-document retrieval. We also find that chunk size correlates moderately with in-document but weakly with in-corpus effectiveness, suggesting segmentation method differences are not purely driven by chunk size. Our code and evaluation benchmarks are publicly available at (Anonymoused).

Reassessing Large Language Model Boolean Query Generation for Systematic Reviews

Systematic reviews are comprehensive literature reviews that address highly focused research questions and represent the highest form of evidence in medicine. A critical step in this process is the development of complex Boolean queries to retrieve relevant literature. Given the difficulty of manually constructing these queries, recent efforts have explored Large Language Models (LLMs) to assist in their formulation. One of the first studies,Wang et al., investigated ChatGPT for this task, followed by Staudinger et al., which evaluated multiple LLMs in a reproducibility study. However, the latter overlooked several key aspects of the original work, including (i) validation of generated queries, (ii) output formatting constraints, and (iii) selection of examples for chain-of-thought (Guided) prompting. As a result, its findings diverged significantly from the original study. In this work, we systematically reproduce both studies while addressing these overlooked factors. Our results show that query effectiveness varies significantly across models and prompt designs, with guided query formulation benefiting from well-chosen seed studies. Overall, prompt design and model selection are key drivers of successful query formulation. Our findings provide a clearer understanding of LLMs' potential in Boolean query generation and highlight the importance of model- and prompt-specific optimisations. The complex nature of systematic reviews adds to challenges in both developing and reproducing methods but also highlights the importance of reproducibility studies in this domain.

LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback

Vector Pseudo Relevance Feedback (VPRF) has shown promising results in improving BERT-based dense retrieval systems through iterative refinement of query representations. This paper investigates the generalizability of VPRF to Large Language Model (LLM) based dense retrievers. We introduce LLM-VPRF and evaluate its effectiveness across multiple benchmark datasets, analyzing how different LLMs impact the feedback mechanism. Our results demonstrate that VPRF's benefits successfully extend to LLM architectures, establishing it as a robust technique for enhancing dense retrieval performance regardless of the underlying models. This work bridges the gap between VPRF with traditional BERT-based dense retrievers and modern LLMs, while providing insights into their future directions.