mlsanityData to 14 Oct 2026

Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Systems: Method and Industrial Evidence-Quality Audit

arXiv 2606.01542 ↗First posted 1 Jun 2026cs.DC cs.AI cs.CLcited by 0

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

Chunked-document retrieval is a common component of retrieval-augmented generation (RAG) systems. Documents are split into overlapping chunks, embedded, and indexed with approximate nearest-neighbor search such as hierarchical navigable small world graphs (HNSW). Overlap improves boundary coverage but induces a practical failure mode: top-k retrieval often returns near-adjacent chunks that repeat evidence and waste prompt budget. We propose Self-Conditioned Positional HNSW (SCP-HNSW), a lightweight modification that appends a low-dimensional positional code to chunk embeddings and uses a two-pass query procedure to estimate and apply a query-specific document-position prior. SCP-HNSW leaves HNSW graph construction and traversal unchanged while adding an auditable minimum-index-gap selector for final context construction. We also integrate industrial review artifacts for generated evidence quality: a 770-review text-evidence audit with 318 fully labeled reviews and a 70-case OCR audit with 350 ratings. The text audit shows that 574 of 770 projected reviews are rated 3/5, only 39 fall in the 1-2 range, and narrative reviewer detail appears much more often than structured issue flags. The OCR audit shows slice-level pass rates from 95% for clean chat screenshots to 45% for handwritten/blurry captures, with moderate to strong agreement. These results motivate overlap-aware, audit-friendly RAG retrieval and identify the remaining controlled retrieval ablations needed for causal performance claims.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 5 of its 13 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

5 of 13 references.

References · 5

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  4. 2021A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Searchcited by 82
  5. 2024ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Datacited by 32

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents
  2. 2025HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking
  3. 2026Adaptive Chunking: Optimizing Chunking-Method Selection for RAG
  4. 2026Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
  5. 2026Graph-Aware Late Chunking for Retrieval-Augmented Generation in Biomedical Literature
  6. 2024ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems
  7. 2026SPIRE: Structure-Preserving Interpretable Retrieval of Evidence
  8. 2026KohakuRAG: A simple RAG framework with hierarchical document indexing