{"id":"https://openalex.org/W7128809525","doi":"https://doi.org/10.48550/arxiv.2602.11908","title":"When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation","display_name":"When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128809525","doi":"https://doi.org/10.48550/arxiv.2602.11908"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.11908","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125969477","display_name":"Shani Goren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goren, Shani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121347481","display_name":"Ido Galil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Galil, Ido","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025669300","display_name":"Ran El\u2010Yaniv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"El-Yaniv, Ran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.33009999990463257,"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":0.33009999990463257,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.26899999380111694,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0348999984562397,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7595000267028809},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.7003999948501587},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6819999814033508},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5476999878883362},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5174000263214111},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4925999939441681}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7595000267028809},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7037000060081482},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7003999948501587},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6819999814033508},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5174000263214111},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.5080999732017517},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4009000062942505},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36399999260902405},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2969000041484833},{"id":"https://openalex.org/C2781472820","wikidata":"https://www.wikidata.org/wiki/Q2154759","display_name":"Risk measure","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27309998869895935},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2597000002861023}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.11908","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.11908","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.11908","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.11908","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLMs":[0,65],"are":[1],"widely":[2],"used,":[3],"yet":[4],"they":[5],"remain":[6],"prone":[7],"to":[8,23,28,66,179],"factual":[9,141],"errors":[10],"that":[11,35,63,100,137,185],"erode":[12],"user":[13],"trust":[14],"and":[15,89,114,143,160,191],"limit":[16],"adoption":[17],"in":[18,49],"high-risk":[19],"settings.":[20],"One":[21],"approach":[22,45],"mitigate":[24],"this":[25,42,126],"risk":[26,88,139],"is":[27,39,46],"equip":[29],"models":[30,156],"with":[31,118],"uncertainty":[32],"estimation":[33],"mechanisms":[34],"abstain":[36],"when":[37],"confidence":[38],"low.":[40],"However,":[41],"binary":[43],"\"all-or-nothing\"":[44],"excessively":[47],"restrictive":[48],"long-form":[50],"settings,":[51],"often":[52],"discarding":[53],"valuable":[54],"information.":[55,152],"We":[56,79,91],"introduce":[57],"Selective":[58,95],"Abstraction":[59],"(SA),":[60],"a":[61,97,111,130],"framework":[62],"enables":[64],"trade":[67],"specificity":[68,187],"for":[69,134],"reliability":[70,192],"by":[71,177],"selectively":[72],"reducing":[73,186],"the":[74,84,158,170,173],"detail":[75],"of":[76,86,150,196],"uncertain":[77,116],"content.":[78],"first":[80],"formalize":[81],"SA":[82,164],"through":[83],"lenses":[85],"selective":[87],"coverage.":[90],"then":[92],"propose":[93],"Atom-wise":[94],"Abstraction,":[96],"claim-level":[98],"instantiation":[99],"decomposes":[101],"responses":[102],"into":[103],"atomic":[104],"claims":[105],"(short,":[106],"self-contained":[107],"statements":[108],"each":[109],"expressing":[110],"single":[112],"fact)":[113],"replaces":[115],"atoms":[117],"higher":[119],"confidence,":[120],"less":[121],"specific":[122],"abstractions.":[123],"To":[124],"evaluate":[125],"framework,":[127],"we":[128],"develop":[129],"novel":[131],"end-to-end":[132],"pipeline":[133],"open-ended":[135],"generation":[136],"instantiates":[138],"as":[140],"correctness":[142],"measures":[144],"coverage":[145],"using":[146],"an":[147],"information-theoretic":[148],"measure":[149],"retained":[151],"Across":[153],"six":[154],"open-source":[155],"on":[157],"FactScore":[159],"LongFact-Objects":[161],"benchmarks,":[162],"atom-wise":[163],"consistently":[165],"outperforms":[166],"existing":[167],"baselines,":[168],"improving":[169],"area":[171],"under":[172],"risk-coverage":[174],"curve":[175],"(AURC)":[176],"up":[178],"27.73%":[180],"over":[181],"claim":[182],"removal,":[183],"demonstrating":[184],"can":[188],"boost":[189],"accuracy":[190],"while":[193],"preserving":[194],"most":[195],"their":[197],"original":[198],"meaning.":[199]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-14T00:00:00"}