{"id":"https://openalex.org/W7224111007","doi":"https://doi.org/10.48550/arxiv.2610.36557","title":"QESChunker: A Single Objective Unifies Overlapping and Non-Overlapping Chunking for RAG","display_name":"QESChunker: A Single Objective Unifies Overlapping and Non-Overlapping Chunking for RAG","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224111007","doi":"https://doi.org/10.48550/arxiv.2610.36557"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.36557","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36557","pdf_url":"https://arxiv.org/pdf/2610.36557","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.36557","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160040957","display_name":"Yifan Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Yifan","raw_affiliation_strings":["Alibaba Group (alibaba-inc.com )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group (alibaba-inc.com )","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138261365","display_name":"Qianyang Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Qianyang","raw_affiliation_strings":["Alibaba Group (alibaba-inc.com )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group (alibaba-inc.com )","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101429563","display_name":"Xinyu Guan","orcid":"https://orcid.org/0009-0000-6901-7925","observed_orcids":["https://orcid.org/0009-0000-6901-7925"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guan, Xinyu","raw_affiliation_strings":["Alibaba Group (alibaba-inc.com )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group (alibaba-inc.com )","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160064051","display_name":"kai wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"wei, kai","raw_affiliation_strings":["Taobao (China) Software Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao (China) Software Co. , Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110790626","display_name":"Yuming Deng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng, Yuming","raw_affiliation_strings":["Alibaba Group (alibaba-inc.com )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group (alibaba-inc.com )","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8461999893188477,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8461999893188477,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.13670000433921814,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/document-chunking","display_name":"document chunking","score":0.9200000166893005},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9940000176429749},{"id":"https://openalex.org/keywords/submodular-optimization","display_name":"submodular optimization","score":0.8389999866485596},{"id":"https://openalex.org/keywords/greedy-approximation","display_name":"greedy approximation","score":0.7580000162124634},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"dynamic programming","score":0.7300000190734863},{"id":"https://openalex.org/keywords/evidence-retrieval","display_name":"evidence retrieval","score":0.7910000085830688}],"concepts":[{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.9214000105857849},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6901999711990356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6712999939918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5436999797821045},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3743000030517578},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2556000053882599},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.36557","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36557","pdf_url":"https://arxiv.org/pdf/2610.36557","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.36557","doi":"https://doi.org/10.48550/arxiv.2610.36557","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.36557","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.36557","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36557","pdf_url":"https://arxiv.org/pdf/2610.36557","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224111007.pdf","grobid_xml":"https://content.openalex.org/works/W7224111007.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2794904608","https://openalex.org/W2970728484","https://openalex.org/W3022669779","https://openalex.org/W4389984066","https://openalex.org/W4403882995","https://openalex.org/W4404781515","https://openalex.org/W4404783040","https://openalex.org/W6910263647"],"related_works":["https://openalex.org/W7216570215","https://openalex.org/W7125098831","https://openalex.org/W7154900482","https://openalex.org/W7163206683","https://openalex.org/W4409183391","https://openalex.org/W7141358750","https://openalex.org/W4416390973","https://openalex.org/W7131883812","https://openalex.org/W7135428656","https://openalex.org/W7162291267"],"abstract_inverted_index":{"Chunking":[0],"is":[1,100,109],"a":[2,65,73,115,144],"fundamental":[3],"preprocessing":[4],"step":[5],"in":[6,92,130,133],"retrieval-augmented":[7],"generation":[8],"(RAG),":[9],"yet":[10],"most":[11],"existing":[12,127],"chunkers":[13],"rely":[14],"primarily":[15],"on":[16],"heuristics.":[17],"We":[18,57],"introduce":[19],"the":[20,27,79,82,102,139],"Question--Evidence-Supervised":[21],"Chunker":[22],"(QESChunker),":[23],"to":[24,53],"our":[25,112],"knowledge":[26],"first":[28],"method":[29],"for":[30,157],"constructing":[31],"static":[32],"chunk":[33,41],"indices":[34,42],"from":[35],"question--evidence":[36,49,67],"supervision.":[37],"QESChunker":[38],"constructs":[39],"document-specific":[40],"by":[43,95],"optimizing":[44],"over":[45,85],"human-annotated":[46],"or":[47],"LLM-generated":[48],"pairs,":[50],"without":[51],"access":[52],"held-out":[54],"test":[55],"queries.":[56],"formulate":[58],"non-overlapping":[59],"and":[60,87,120,143],"overlapping":[61],"index":[62,155],"construction":[63,156],"through":[64],"unified":[66],"utility-maximization":[68],"objective,":[69],"turning":[70],"chunking":[71,128,151],"into":[72],"supervised":[74],"combinatorial":[75],"optimization":[76,108],"problem.":[77],"Under":[78],"non-overlap":[80],"constraint,":[81],"objective":[83,103],"decomposes":[84],"chunks":[86],"can":[88],"be":[89],"optimized":[90],"exactly":[91],"polynomial":[93],"time":[94],"dynamic":[96],"programming.":[97],"When":[98],"overlap":[99,141],"allowed,":[101],"becomes":[104],"monotone":[105],"submodular;":[106],"exact":[107],"NP-hard,":[110],"but":[111],"greedy":[113],"achieves":[114],"$(1-1/\\sqrt{e})$-approximation.":[116],"Across":[117],"two":[118],"self-constructed":[119],"three":[121],"public":[122],"datasets,":[123],"both":[124],"variants":[125],"outperform":[126],"methods":[129],"complete-evidence":[131],"recall":[132],"nearly":[134],"all":[135],"evaluated":[136],"settings,":[137],"under":[138],"same":[140],"regime":[142],"fixed":[145],"hybrid":[146],"retriever.":[147],"These":[148],"results":[149],"recast":[150],"as":[152],"supervised,":[153],"budget-aware":[154],"evidence":[158],"retrieval.":[159]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-29T00:00:00"}