mlsanityData to 14 Oct 2026

Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation

arXiv 2604.19777 ↗First posted 28 Mar 2026cs.CL cs.AI cs.IRcited by 1

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) exhibit a well-documented positional bias when processing long input contexts: information in the middle of a context window receives substantially less attention than content at the boundaries, a phenomenon termed the Lost-in-the-Middle effect (Liu et al., 2024). This limits knowledge-retrieval applications that embed large structured knowledge bases directly in the LLM context. Retrieval-Augmented Generation (RAG) addresses scalability by retrieving only relevant fragments, but introduces substantial infrastructure overhead and is ill-suited to libraries whose semantic boundaries are human-defined rather than statistically learned. We propose Self-Describing Structured Retrieval (SDSR), a lightweight framework in which structured data files embed human-authored navigational metadata at the file's primacy position, thereby exploiting rather than fighting the LLM's primacy bias. We further propose a Dual-Layer Guidance strategy combining in-file metadata with explicit routing rules in the system prompt. We validate SDSR through a four-round benchmark using a 190-skill library expanded from 36 to 119 categories via adversarial distractor injection. Four conditions are tested: (A) no guidance, (B) in-file summary only, (C) prompt hint only, (D) both combined. Version D achieves 100% primary routing accuracy (20/20) at 119 categories versus 65% for the no-guidance baseline. We identify a fundamental asymmetry: primary routing is solvable by explicit rules, while secondary cross-category routing requires architectural intent explicitly encoded in the data structure. We further extend SDSR to semi-structured corpora, showing how cross-reference encoding enables operation without vector databases in domains with recoverable document structure.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 40 references that are in the map. First posted on arXiv 28 Mar 2026.

Builds on

14 of 40 references.

References · 14

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  4. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  5. 2024Data Engineering for Scaling Language Models to 128K Contextcited by 186
  6. 2024Make Your LLM Fully Utilize the Contextcited by 119
  7. 2024Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffoldingcited by 117
  8. 2024Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encodingcited by 72
  9. 2024Eliminating Position Bias of Language Models: A Mechanistic Approachcited by 65
  10. 2025On the Emergence of Position Bias in Transformerscited by 59
  11. 2024Serial Position Effects of Large Language Modelscited by 30
  12. 2024Position Engineering: Boosting Large Language Models through Positional Information Manipulationcited by 9
2 more
  1. 2025Lost in the Middle: An Emergent Property from Information Retrieval Demands in LLMscited by 9
  2. 2024Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspectivecited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026From Explicit Elements to Implicit Intent: A Predefined Library for Auditable Behavioral Inferencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely
  2. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  3. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  4. 2025Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models
  5. 2025RAG-Anything: All-in-One RAG Framework
  6. 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing
  7. 2025Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding
  8. 2026Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection