{
  "abstract": "Chunking is a fundamental preprocessing step in retrieval-augmented generation (RAG), yet most existing chunkers rely primarily on heuristics. We introduce the Question--Evidence-Supervised Chunker (QESChunker), to our knowledge the first method for constructing static chunk indices from question--evidence supervision. QESChunker constructs document-specific chunk indices by optimizing over human-annotated or LLM-generated question--evidence pairs, without access to held-out test queries. We formulate non-overlapping and overlapping index construction through a unified question--evidence utility-maximization objective, turning chunking into a supervised combinatorial optimization problem. Under the non-overlap constraint, the objective decomposes over chunks and can be optimized exactly in polynomial time by dynamic programming. When overlap is allowed, the objective becomes monotone submodular; exact optimization is NP-hard, but our greedy achieves a $(1-1/\\sqrt{e})$-approximation. Across two self-constructed and three public datasets, both variants outperform existing chunking methods in complete-evidence recall in nearly all evaluated settings, under the same overlap regime and a fixed hybrid retriever. These results recast chunking as supervised, budget-aware index construction for evidence retrieval.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.36557",
  "author_total": 5,
  "authors": [
    {
      "name": "Yifan Zhao"
    },
    {
      "name": "Qianyang Zhao"
    },
    {
      "name": "Xinyu Guan"
    },
    {
      "name": "kai wei"
    },
    {
      "name": "Yuming Deng"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/19g692bzqacy3.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.36557",
  "fulltext_url": null,
  "id": "19g692bzqacy3",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.36557",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CL"
    ],
    [
      "arxiv",
      "cs.IR"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "openalex",
      "1702|Topic Modeling"
    ]
  ],
  "openalex": "W7224111007",
  "pdf_url": "https://arxiv.org/pdf/2610.36557",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-27",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/19g692bzqacy3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:53Z",
      "native_id": "2610.36557",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.36557"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "QESChunker: A Single Objective Unifies Overlapping and Non-Overlapping Chunking for RAG",
  "title_text": "QESChunker: A Single Objective Unifies Overlapping and Non-Overlapping Chunking for RAG",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:53Z",
  "url": "https://research.draconitic.com/paper/19g692bzqacy3",
  "venue": "arXiv",
  "versions": []
}