NuggetIndex: Governed Atomic Retrieval for Maintainable RAG

• URL: http://arxiv.org/abs/2604.27306v1
• Date: Thu, 30 Apr 2026 01:33:56 GMT
• Title: NuggetIndex: Governed Atomic Retrieval for Maintainable RAG
• Abstract summary: We propose NuggetIndex, a retrieval system that stores atomic information units as managed records, so called nuggets.<n>Each record maintains links to evidence, a temporal validity interval, and a lifecycle state.<n>We evaluate the approach using a nuggetized MS MARCO subset, a temporal Wikipedia QA dataset, and a multi-hop QA task.
• Score: 3.2058241360543254
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-augmented generation (RAG) systems are frequently evaluated via fact-based metrics, yet standard implementations retrieve passages or static propositions. This unit mismatch between evaluation and retrieval objects hinders maintenance when corpora evolve and fails to capture superseded facts or source disagreements. We propose NuggetIndex, a retrieval system that stores atomic information units as managed records, so called nuggets. Each record maintains links to evidence, a temporal validity interval, and a lifecycle state. By filtering invalid or deprecated nuggets prior to ranking, the system prevents the inclusion of outdated information. We evaluate the approach using a nuggetized MS MARCO subset, a temporal Wikipedia QA dataset, and a multi-hop QA task. Against passage and unmanaged proposition retrieval baselines, NuggetIndex improves nugget recall by 42%, increases temporal correctness by 9 percentage points without the recall collapse observed in time-filtered baselines, and reduces conflict rates by 55%. The compact nugget format reduces generator input length by 64% while enabling lightweight index structures suitable for browser-based and resource-constrained deployment. We release our implementation, datasets, and evaluation scripts

Related papers

• Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops [11.99667127177886]
  We show that repeated metric-driven code editing leads to genuine improvements that generalize beyond the loop.<n>We propose a lightweight mitigation that combines category-coverage reweighting, persistent edit memory, and a validation gate.
  arXiv  Detail & Related papers  (2026-08-31T08:11:19Z)
• MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations [50.24315431387575]
  We introduce MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations.<n>MemOps represents each memory event with a structured trace specifying its trigger, target, scope, state transition, and supporting evidence.<n>Across long-context, retrieval-based, parametric and managed-memory systems, MemOps disentangles failure modes that final-answer accuracy alone conceals.
  arXiv  Detail & Related papers  (2026-07-14T15:33:44Z)
• DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation [41.38684270729433]
  DoGMaTiQ is a pipeline for generating high-quality QA-based nugget sets.<n>We integrate DoGMaTiQ with AutoArgue to enable fully automatic evaluation of generated reports.
  arXiv  Detail & Related papers  (2026-05-06T03:34:46Z)
• Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering [0.0]
  This study explores chunk filtering strategies to reduce the indexed corpus while preserving retrieval quality.<n>Retrieval performance is evaluated using a token-based framework based on precision, recall, and intersection-over-union metrics.
  arXiv  Detail & Related papers  (2026-04-27T11:23:39Z)
• A Parametric Memory Head for Continual Generative Retrieval [52.66674234249913]
  Generative information retrieval (GenIR) consolidates retrieval into a single neural model that decodes document identifiers (docids) directly from queries.<n>We show that sequential adaptation improves retrieval on newly added documents but substantially degrades performance on earlier slices.<n>We propose post-adaptation memory tuning (PAMT), a memory-only stabilization stage that augments an adapted model with a modular parametric memory head.
  arXiv  Detail & Related papers  (2026-04-25T17:38:51Z)
• FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation [73.22935457705057]
  We introduce FRESCO, a benchmark for evaluating re-rankers in temporally dynamic contexts.<n>By pairing recency-seeking queries with historical Wikipedia revisions, FRESCO tests whether re-rankers can prioritize factually recent evidence while maintaining semantic relevance.<n>Our evaluation reveals a consistent failure mode across existing re-rankers: a strong bias toward older, semantically rich documents, even when they are factually obsolete.
  arXiv  Detail & Related papers  (2026-04-14T17:04:25Z)
• Incorporating Q&A Nuggets into Retrieval-Augmented Generation [23.32167679162754]
  Crucible is a Nugget-Augmented Generation System that preserves explicit citation provenance by constructing a bank of Q&A nuggets from retrieved documents.<n> Reasoning on nuggets avoids repeated information through clear and interpretable Q&A semantics.<n>Our system substantially outperforms Ginger, a recent nugget-based RAG system, in nugget recall, density, and citation grounding.
  arXiv  Detail & Related papers  (2026-01-19T16:57:33Z)
• Memory in Large Language Models: Mechanisms, Evaluation and Evolution [8.158439933515131]
  We propose a four-part taxonomy (parametric, contextual, external, procedural/episodic) and a memory quadruple (location, persistence, write/access path, controllability)<n>For updating and forgetting, we present DMM Gov: coordinating DAPT/TAPT, PEFT, model editing (ROME, MEND, MEMIT, SERAC), and RAG to form an auditable loop.<n>This yields a reproducible, comparable, and governable coordinate system for research and deployment.
  arXiv  Detail & Related papers  (2025-09-23T10:06:58Z)
• Chatbot Arena Meets Nuggets: Towards Explanations and Diagnostics in the Evaluation of LLM Responses [45.2769075498271]
  We apply our AutoNuggetizer framework to analyze data from roughly 7K Search Arena battles provided by LMArena.<n>Our results show a significant correlation between nugget scores and human preferences.
  arXiv  Detail & Related papers  (2025-04-28T17:24:36Z)
• The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models [53.12387628636912]
  We propose an automatic evaluation framework that is validated against human annotations.<n>This approach was originally developed for the TREC Question Answering (QA) Track in 2003.<n>We observe strong agreement at the run level between scores derived from fully automatic nugget evaluation and human-based variants.
  arXiv  Detail & Related papers  (2025-04-21T12:55:06Z)
• Atomic Fact Decomposition Helps Attributed Question Answering [29.67882325906939]
  Attributed Question Answering (AQA) aims to provide both a trustworthy answer and a reliable attribution report for a question.<n>This paper proposes an Atomic fact decomposition-based Retrieval and Editing framework.<n>It decomposes the generated long-form answers into molecular clauses and atomic facts by the instruction-tuned LLMs.
  arXiv  Detail & Related papers  (2024-10-22T05:25:54Z)
• SparseCL: Sparse Contrastive Learning for Contradiction Retrieval [87.02936971689817]
  Contradiction retrieval refers to identifying and extracting documents that explicitly disagree with or refute the content of a query. Existing methods such as similarity search and crossencoder models exhibit significant limitations. We introduce SparseCL that leverages specially trained sentence embeddings designed to preserve subtle, contradictory nuances between sentences.
  arXiv  Detail & Related papers  (2024-06-15T21:57:03Z)
• Detection Transformer with Stable Matching [48.963171068785435]
  We show that the most important design is to use and only use positional metrics to supervise classification scores of positive examples. Under the principle, we propose two simple yet effective modifications by integrating positional metrics to DETR's classification loss and matching cost. We achieve 50.4 and 51.5 AP on the COCO detection benchmark using ResNet-50 backbones under 12 epochs and 24 epochs training settings.
  arXiv  Detail & Related papers  (2023-04-10T17:55:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.