{"id":"https://openalex.org/W4412396177","doi":"https://doi.org/10.1145/3726302.3729882","title":"A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking","display_name":"A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412396177","doi":"https://doi.org/10.1145/3726302.3729882"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3729882","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729882","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729882","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729882","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063325405","display_name":"Henrik Br\u00e5dland","orcid":"https://orcid.org/0000-0002-1601-8884"},"institutions":[{"id":"https://openalex.org/I200650556","display_name":"University of Agder","ror":"https://ror.org/03x297z98","country_code":"NO","type":"education","lineage":["https://openalex.org/I200650556"]},{"id":"https://openalex.org/I4210119947","display_name":"Agder Research","ror":"https://ror.org/02k3w5n89","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210119947"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Henrik Br\u00e5dland","raw_affiliation_strings":["Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Agder, Norway and Norkart AS, Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-1601-8884","affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Agder, Norway and Norkart AS, Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I200650556","https://openalex.org/I4210119947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002394922","display_name":"Morten Goodwin","orcid":"https://orcid.org/0000-0001-6331-702X"},"institutions":[{"id":"https://openalex.org/I200650556","display_name":"University of Agder","ror":"https://ror.org/03x297z98","country_code":"NO","type":"education","lineage":["https://openalex.org/I200650556"]},{"id":"https://openalex.org/I4210119947","display_name":"Agder Research","ror":"https://ror.org/02k3w5n89","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210119947"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Morten Goodwin","raw_affiliation_strings":["Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Agder, Norway"],"raw_orcid":"https://orcid.org/0000-0001-6331-702X","affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Agder, Norway","institution_ids":["https://openalex.org/I200650556","https://openalex.org/I4210119947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088348597","display_name":"Per\u2010Arne Andersen","orcid":"https://orcid.org/0000-0002-7742-4907"},"institutions":[{"id":"https://openalex.org/I200650556","display_name":"University of Agder","ror":"https://ror.org/03x297z98","country_code":"NO","type":"education","lineage":["https://openalex.org/I200650556"]},{"id":"https://openalex.org/I4210119947","display_name":"Agder Research","ror":"https://ror.org/02k3w5n89","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210119947"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Per-Arne Andersen","raw_affiliation_strings":["Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Agder, Norway"],"raw_orcid":"https://orcid.org/0000-0002-7742-4907","affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Agder, Norway","institution_ids":["https://openalex.org/I200650556","https://openalex.org/I4210119947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013125971","display_name":"Alexander Salveson Nossum","orcid":"https://orcid.org/0009-0005-1769-3194"},"institutions":[{"id":"https://openalex.org/I4210135856","display_name":"NRK (Norway)","ror":"https://ror.org/03se59c70","country_code":"NO","type":"company","lineage":["https://openalex.org/I4210135856"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Alexander S. Nossum","raw_affiliation_strings":["Norkart AS, Oslo, Norway"],"raw_orcid":"https://orcid.org/0009-0005-1769-3194","affiliations":[{"raw_affiliation_string":"Norkart AS, Oslo, Norway","institution_ids":["https://openalex.org/I4210135856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017136504","display_name":"Aditya Gupta","orcid":"https://orcid.org/0000-0003-3128-2517"},"institutions":[{"id":"https://openalex.org/I200650556","display_name":"University of Agder","ror":"https://ror.org/03x297z98","country_code":"NO","type":"education","lineage":["https://openalex.org/I200650556"]},{"id":"https://openalex.org/I4210119947","display_name":"Agder Research","ror":"https://ror.org/02k3w5n89","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210119947"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Aditya Gupta","raw_affiliation_strings":["Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Agder, Norway"],"raw_orcid":"https://orcid.org/0000-0003-3128-2517","affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Agder, Norway","institution_ids":["https://openalex.org/I200650556","https://openalex.org/I4210119947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063325405"],"corresponding_institution_ids":["https://openalex.org/I200650556","https://openalex.org/I4210119947"],"apc_list":null,"apc_paid":null,"fwci":15.2128,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98766152,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9950000047683716,"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/T12031","display_name":"Speech and dialogue systems","score":0.9912999868392944,"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/chunking","display_name":"Chunking (psychology)","score":0.8226548433303833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7850831747055054},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5361184477806091},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5208255052566528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.494265079498291},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.053125590085983276}],"concepts":[{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.8226548433303833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850831747055054},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5361184477806091},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5208255052566528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.494265079498291},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.053125590085983276},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3726302.3729882","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729882","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729882","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.02171","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.02171","pdf_url":"https://arxiv.org/pdf/2505.02171","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"doi:10.1145/3726302.3729882","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729882","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729882","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5799999833106995,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412396177.pdf","grobid_xml":"https://content.openalex.org/works/W4412396177.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2082349168","https://openalex.org/W2133102095","https://openalex.org/W3137305332","https://openalex.org/W4321094913","https://openalex.org/W4365129631","https://openalex.org/W4386576685","https://openalex.org/W4389523979","https://openalex.org/W4391376033","https://openalex.org/W4399530612","https://openalex.org/W4400525811","https://openalex.org/W4401042011","https://openalex.org/W4404782396","https://openalex.org/W4410636953"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384729545","https://openalex.org/W2198395236","https://openalex.org/W4245487161","https://openalex.org/W2090755435","https://openalex.org/W2039036070","https://openalex.org/W2153813398","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Document":[0],"chunking":[1,43,58,163],"fundamentally":[2],"impacts":[3],"Retrieval-Augmented":[4],"Generation":[5],"(RAG)":[6],"by":[7],"determining":[8],"how":[9],"source":[10],"materials":[11],"are":[12,22],"segmented":[13],"before":[14],"indexing.Despite":[15],"evidence":[16],"that":[17,52,82,94],"Large":[18],"Language":[19],"Models":[20],"(LLMs)":[21],"sensitive":[23],"to":[24,37,134,170],"the":[25,39,57,95,111,144],"layout":[26],"and":[27,69,84,115,139],"structure":[28],"of":[29,41,56,113,118,132],"retrieved":[30],"data,":[31],"there":[32],"is":[33],"currently":[34],"no":[35],"framework":[36],"analyze":[38],"impact":[40],"different":[42],"methods.In":[44],"this":[45],"paper,":[46],"we":[47],"introduce":[48],"a":[49,77,129],"novel":[50],"methodology":[51],"defines":[53],"essential":[54,124],"characteristics":[55],"process":[59],"at":[60],"three":[61],"levels:":[62],"intrinsic":[63,116],"passage":[64,67],"properties,":[65,68],"extrinsic":[66,114],"passages-document":[70],"coherence.We":[71],"propose":[72],"HOPE":[73,96],"(Holistic":[74],"Passage":[75],"Evaluation),":[76],"domain-agnostic,":[78],"automatic":[79],"evaluation":[80],"metric":[81,97],"quantifies":[83],"aggregates":[85],"these":[86],"characteristics.Our":[87],"empirical":[88],"evaluations":[89],"across":[90],"seven":[91],"domains":[92],"demonstrate":[93],"correlates":[98],"significantly":[99],"(":[100],">":[101],"0.13)":[102],"with":[103,128],"various":[104],"RAG":[105,167],"performance":[106,127,130],"indicators,":[107],"revealing":[108],"contrasts":[109],"between":[110,121],"importance":[112],"properties":[117],"passages.Semantic":[119],"independence":[120],"passages":[122,153],"proves":[123],"for":[125,161],"system":[126,168],"gain":[131],"up":[133],"56.2%":[135],"in":[136,141],"factual":[137],"correctness":[138],"21.1%":[140],"answer":[142],"correctness.On":[143],"contrary,":[145],"traditional":[146],"assumptions":[147],"about":[148],"maintaining":[149],"concept":[150],"unity":[151],"within":[152],"show":[154],"minimal":[155],"impact.These":[156],"findings":[157],"provide":[158],"actionable":[159],"insights":[160],"optimizing":[162],"strategies,":[164],"thus":[165],"improving":[166],"design":[169],"produce":[171],"more":[172],"factually":[173],"correct":[174],"responses.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}