{"id":"https://openalex.org/W7166817442","doi":"https://doi.org/10.18653/v1/2026.acl-long.66","title":"SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA","display_name":"SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166817442","doi":"https://doi.org/10.18653/v1/2026.acl-long.66"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.66","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.66","pdf_url":"https://aclanthology.org/2026.acl-long.66.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.66.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042267620","display_name":"Sher Badshah","orcid":"https://orcid.org/0000-0001-6780-3746"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sher Badshah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139812448","display_name":"Ali Emami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Emami","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139781796","display_name":"Hassan Sajjad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hassan Sajjad","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80694755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1466","last_page":"1491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.54830002784729,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.54830002784729,"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/T10028","display_name":"Topic Modeling","score":0.16359999775886536,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.029100000858306885,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/natural-language","display_name":"Natural language","score":0.32429999113082886},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2824000120162964},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.26080000400543213},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.25119999051094055},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.25099998712539673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6424999833106995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45590001344680786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.450300008058548},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2363000065088272},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.23149999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.66","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.66","pdf_url":"https://aclanthology.org/2026.acl-long.66.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.66","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.66","pdf_url":"https://aclanthology.org/2026.acl-long.66.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6840340495109558}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330759","display_name":"Research Nova Scotia","ror":null},{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166817442.pdf","grobid_xml":"https://content.openalex.org/works/W7166817442.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"become":[5],"increasingly":[6],"used":[7],"for":[8,16,36,126],"question-answering":[9],"(QA),":[10],"relying":[11],"on":[12,51,83,114,133],"static,":[13],"pre-annotated":[14],"references":[15,79],"evaluation":[17,117],"poses":[18],"significant":[19],"challenges":[20],"in":[21],"cost,":[22],"scalability,":[23],"and":[24,48,94,106,123],"completeness.Meanwhile,":[25],"using":[26],"LLMs":[27],"themselves":[28],"as":[29,39,88],"evaluators":[30],"without":[31,69],"external":[32,96],"grounding":[33],"remains":[34],"unreliable":[35],"objective":[37],"tasks,":[38],"they":[40],"systematically":[41],"over-accept":[42],"incorrect":[43],"answers,":[44],"fabricate":[45],"supporting":[46],"rationales,":[47],"degrade":[49],"sharply":[50],"questions":[52],"that":[53,75,91,139],"fall":[54],"outside":[55],"their":[56],"training":[57],"data.We":[58],"propose":[59],"Search-AuGmented":[60],"Evaluation":[61],"(SAGE),":[62],"a":[63,121],"framework":[64],"to":[65,77,143],"assess":[66],"LLM":[67],"outputs":[68],"fixed":[70],"groundtruth":[71],"answers.Unlike":[72],"conventional":[73],"metrics":[74],"compare":[76],"static":[78,115],"or":[80],"depend":[81],"solely":[82],"LLM-as-a-judge":[84],"knowledge,":[85],"SAGE":[86,119,140],"acts":[87],"an":[89],"agent":[90],"actively":[92],"retrieves":[93],"synthesizes":[95],"evidence.It":[97],"iteratively":[98],"generates":[99],"web":[100],"queries,":[101],"collects":[102],"information,":[103],"summarizes":[104],"findings,":[105],"refines":[107],"subsequent":[108],"searches":[109],"through":[110],"reflection.By":[111],"reducing":[112],"dependence":[113],"reference-driven":[116],"protocols,":[118],"offers":[120],"scalable":[122],"adaptive":[124],"alternative":[125],"evaluating":[127],"the":[128],"factuality":[129],"of":[130],"LLMs.Experimental":[131],"results":[132],"multiple":[134],"free-form":[135],"QA":[136],"benchmarks":[137],"show":[138],"achieves":[141],"substantial":[142],"perfect":[144],"agreement":[145],"with":[146],"human":[147],"evaluations.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
