{"slug": "chunk-recomputation-under-real-document-revisions-measuring-update-cost-and-of", "title": "Chunk Recomputation under Real Document Revisions: Measuring Update Cost and Retrieval Quality of Fixed, Recursive, and Content-Defined Chunking", "summary": "A study of 120 pairs of adjacent Chinese and English Wikipedia revisions found that fixed-size chunking recomputes 57-68% of its full new-version embedding-input workload after edits, versus 38-56% for recursive paragraph-first chunking and 43-54% for content-defined chunking, under a strict byte-identical reuse rule with a frozen dense encoder. On the 116-article common-success pool, mean evidence recall under a fixed 2048-token retrieval budget differed by less than two percentage points within either language, and content-defined chunking failed on 4 of 62 Chinese articles. The authors, posting as arXiv:2610.31019v1, conclude that update cost is a parameter-sensitive dimension static retrieval evaluations do not expose and should be reported alongside retrieval quality.", "body_md": "arXiv:2610.31019v1 Announce Type: new \nAbstract: Chunking strategies for retrieval-augmented generation are almost always evaluated on a static snapshot, yet the documents underlying a knowledge base continue to change. Because chunks are embedded independently, a boundary that moves after an edit forces unchanged text to be re-embedded. We measure this update cost on 120 pairs of adjacent Chinese and English Wikipedia revisions for three stateless chunkers (non-overlapping fixed-size, recursive paragraph-first, and content-defined chunking) under a strict byte-identical reuse rule and a frozen dense encoder. On the 116-article common-success pool, with frozen, length-calibrated parameters, fixed-size chunking recomputes 57-68% of its full new-version embedding-input workload, recursive chunking 38-56%, and content-defined chunking 43-54% (it failed on 4 of 62 Chinese articles), while at these parameters mean evidence recall under a fixed 2048-token retrieval budget differs by less than two percentage points within either language. A cost-only parameter grid shows that the ranking of the two content-aware chunkers changes with chunk-length settings, whereas non-overlapping fixed-size chunking has the highest recomputation cost in every length-matched condition. Controlled edits and a verbatim-presence diagnostic support boundary drift as one contributor to recomputation of text already present in the previous version. Update cost is therefore a substantial, parameter-sensitive dimension that static retrieval evaluations do not expose and that should be reported alongside retrieval quality.", "url": "https://wpnews.pro/news/chunk-recomputation-under-real-document-revisions-measuring-update-cost-and-of", "canonical_source": "https://www.machinebrief.com/news/chunk-recomputation-under-real-document-revisions-measuring-zmbd", "published_at": "2026-10-23 04:00:00+00:00", "updated_at": "2026-10-23 04:42:40.824415+00:00", "lang": "en", "topics": ["ai-research", "natural-language-processing", "large-language-models", "ai-infrastructure"], "entities": ["arXiv", "Wikipedia", "retrieval-augmented generation"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/chunk-recomputation-under-real-document-revisions-measuring-update-cost-and-of", "markdown": "https://wpnews.pro/news/chunk-recomputation-under-real-document-revisions-measuring-update-cost-and-of.md", "text": "https://wpnews.pro/news/chunk-recomputation-under-real-document-revisions-measuring-update-cost-and-of.txt", "jsonld": "https://wpnews.pro/news/chunk-recomputation-under-real-document-revisions-measuring-update-cost-and-of.jsonld"}}