Jul 2026· Annual International ACM SIGIR Conference on Research and Development in Information Retrieval· pp. 4087-4092· 0 citations· 26 references
Computer Science
TL;DR
Banana (Bounded Adaptive Navigation Architecture for Nested Archives) replaces opaque vectors with plain-text Markdown indices built via one-time VLM page transcription, eliminating both a separate Optical Character Recognition (OCR) engine and a vector store.
Abstract
Retrieval-augmented question answering (QA) over enterprise PDF archives frequently produces confident near-miss answers because dense embeddings discard entity identity, numerical units, and document provenance. Plain-text indices preserve the entity, unit, and provenance signals that dense embeddings discard. Banana (Bounded Adaptive Navigation Architecture for Nested Archives) replaces opaque vectors with plain-text Markdown indices built via one-time VLM page transcription, eliminating both a separate Optical Character Recognition (OCR) engine and a vector store. At query time it applies Progressive Retrieval with Overlap (PRO), an iterative selector with a deterministic contraction bound, followed by a K-adaptive extraction gate that escalates retrieval depth only upon evidence insufficiency. Across three benchmarks, Banana consistently outperforms the strongest baseline: 71.4~EM on TAT-DQA (+15.2 over PageIndex; p <0.001), within 5.2 of oracle TAT-LLM; 79.3% accuracy on FinanceBench-150 across 53K~pages (+17.3 over PageIndex; p <0.01); and 86.2% Completeness@10 on UniDoc-Bench across 8~domains (+20.8 over the strongest fusion baseline). All gains hold across multiple backbones, including a local model at zero API cost.
Modern language models and agents increasingly require persistent memory for complete codebases, long interaction histories, and heterogeneous enterprise records. The key challenge is to keep hundreds of millions of tokens searchable while passing only bounded source evidence to the answer model. We introduce MegaMem, a source-resolved dual-view retrieval system that separates semantic access from generation evidence. Distilled records and detailed evidence are searched with original and transformed queries; every distilled hit resolves to an immutable source ID before reciprocal-rank fusion, deduplication, and cross-encoder reranking; and only the highest-ranked detailed evidence within a fixed budget supports generation. Post-answer attribution then identifies which loaded sources support the fixed answer. We evaluate MegaMem on EnterpriseRAG-Bench, which contains more than 500,000 heterogeneous enterprise documents and approximately 650M tokens. MegaMem improves Overall from 68.22 to 82.26 and reaches 86.50 Correctness. These results show that MegaMem supports ultra-large persistent memory while preserving strong answer accuracy under a bounded generation context. By separating searchable memory scale from answer-context size, MegaMem provides a practical path toward accurate retrieval over memories ranging from hundreds of millions to one billion tokens. Our code is available at https://github.com/ xfab-xinyuansong/MegaMem.git.
Xinyuan Song, Bowen Zhu, H. Haque et al.· 0 citations
Large language models (LLMs) have changed enterprise knowledge work. Their value, however, is capped by three failures: they hallucinate, their parametric memory is frozen and grows stale, and they cannot read the proprietary data that holds most business answers. Retrieval-Augmented Generation (RAG) targets all three. It grounds generation in passages fetched at inference time from an external, continuously updatable corpus, so answers become verifiable and citation-backed without any model retraining. This paper presents a technical synthesis of RAG for trustworthy enterprise assistants. The end-to-end pipeline is described in full: document chunking, embedding, vector indexing, retrieval, cross-encoder re-ranking, and grounded generation with inline citations. Advanced variants are then surveyed, namely hybrid sparse-dense retrieval, Hypothetical Document Embeddings (HyDE), graph-based RAG, and agentic iterative retrieval. A RAGAS-style evaluation method quantifies faithfulness, answer relevance, and context precision and recall. On an illustrative enterprise question-answering scenario, an advanced configuration that combines hybrid retrieval with cross-encoder re-ranking lifts faithfulness from 0.71 to 0.91 and context precision from 0.62 to 0.84 over naive dense-only RAG. Agentic retrieval reaches 0.95 faithfulness, but pays for it in latency. Enterprise concerns, including document-level access control, data security, cost, and latency budgets, are treated as first-class design constraints. The reported metrics are illustrative. They characterise representative trade-offs rather than a specific deployed study.
Bini P B· International Journal of Inf...· 0 citations
Answering questions over a set of transactional legal documents is most simply done by injecting the whole corpus into the LLM's context window on every query. That baseline maximises retrieval recall, but its token footprint scales with the corpus rather than the question, and long-context degradation scales with it. We report what it took to replace full-corpus injection in a legal-document analysis system, comparing it against two structured retrieval modes over our proprietary structure-aware chunking: embedding retrieval (NAVEMBED) and LLM navigation over a compact structured index (NAVINDEX). On a 20-question benchmark with verified ground-truth answers, a position-bias-controlled, reference-anchored pairwise judge scored semantic retrieval with reranking tied with injection on 16 of 18 document-bound questions (injection preferred on 2) while attending to 17.3x fewer input tokens (a general-text-embedding (GTE) configuration reaches 29.9x at a lower tie rate); both modes were judged tied on the 2 out-of-scope controls. NAVINDEX was judged tied on all 18 at a 1.61x smaller total token footprint, a ~56x smaller answering context, and 25% lower dollar cost. We derive a closed-form caching-crossover rule: cached injection is cheaper in dollars only while the corpus stays below roughly ten times the retrieval payload. Scope and uncertainty are quantified in Section 8.
Mahmoud Hany, Mourad ElSheraey, Mahmoud Said et al.· 0 citations
Retrieval-augmented generation relies mostly on flat, fixed-granularity indexes: documents are cut into uniform chunks and retrieved by similarity, discarding the hierarchical structure of the source. We introduce Semantic Compression Trees (SCT), a hierarchical index in which each node stores only its semantic residual -- the information it adds beyond its parent -- and retrieval proceeds by progressive descent from the root, so that per-query cost is governed by tree depth rather than collection size. We evaluate on QASPER (50 papers, 173 questions) under two protocols differing only in whether the benchmark supplies the relevant document, with bootstrap confidence intervals and paired significance tests throughout. The results are mixed and we report them as such. When the document is given, SCT with a zero-LLM extractive compressor matches dense retrieval on answer quality (0.274 vs. 0.277 F1, $p = 0.37$) using 30% fewer context tokens and no LLM calls to build the index, and residual storage beats storing full summaries at each node (0.274 vs. 0.205, $p<0.001$). Increasing the collection fifty-fold multiplies flat retrieval's per-query scoring work by 48.9x and SCT's by 6.4x. Progressive descent itself is not supported. Retrieving the same residuals without the tree performs identically when the document is given ($p = 0.27$), and descent is substantially worse when the system must select the document (0.122 vs. 0.165, $p<0.001$). Routing accuracy localises the cause: descent selects the correct paper 20.2% of the time against 39.3% for flat retrieval, because that choice is made from the root residual, the most compressed node in the tree. We conclude that the residual representation is worth keeping and top-down routing is not.
Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents -- financial statements, audit reports, regulatory returns -- this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.8% of content lines are table rows, thousands of near-identical figures compete in one embedding space, and a figure inherits its unit from a header a median of 13 lines above it -- so a chunk boundary routinely separates a number from whether it is in lakh or crore, an error of two orders of magnitude. A table-aware chunker built as a steelman fixes the unit problem but leaves 27-30% of numeric chunks with no fiscal-year header at every chunk size we tried. We propose READ (Reliable Embedding-free Agentic Document-search), in which an agent reads the raw document through three deterministic operations -- normalized lexical search, structural navigation, and bounded span reads -- exposed over the Model Context Protocol, so a trajectory is a replayable audit trail, not an opaque similarity score. On 51 verified questions READ answers 58.8% against dense retrieval's 15.7% (p_Holm = 2 x 10^-5) -- or 35.3% tuned, which READ still leads by 23.5 points (p_Holm = 0.017). An agent given the same loop but a top-k tool reaches only 27.5%, locating the gain in the interface rather than in iteration. We also report what the evidence does not support: BM25 is statistically indistinguishable from READ, so our result separates embedding-based from embedding-free retrieval, not agentic from lexical search.
This work presents an end-to-end archival processing and retrieval framework that integrates large language models (LLMs) into the archival pipeline and demonstrates that integrating LLMs with established document processing and retrieval pipelines can elevate digital libraries from static repositories to interactive, semantically searchable archival systems.
Stergios Konstantinidis, Hayman Lotfy, Alexis Erne et al.· 0 citations