{"id":"https://openalex.org/W7138921780","doi":"https://doi.org/10.1609/aaai.v40i46.41277","title":"EvalQAG: A Framework for Automatic Complex QA Generation and a Benchmark QA Dataset for Policy Documents","display_name":"EvalQAG: A Framework for Automatic Complex QA Generation and a Benchmark QA Dataset for Policy Documents","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138921780","doi":"https://doi.org/10.1609/aaai.v40i46.41277"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i46.41277","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i46.41277","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41277/45238","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41277/45238","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130054732","display_name":"Kirtan Brijeshbhai Soni","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Kirtan Brijeshbhai Soni","raw_affiliation_strings":["Dhirubhai Ambani University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129878683","display_name":"Krish Rupapara","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krish Rupapara","raw_affiliation_strings":["Dhirubhai Ambani University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075250646","display_name":"Arpit Rana","orcid":"https://orcid.org/0000-0002-6129-9582"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arpit Rana","raw_affiliation_strings":["Smart Energy Learning Centre, Dhirubhai Ambani University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Smart Energy Learning Centre, Dhirubhai Ambani University","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063962595","display_name":"Ghanshyam Verma","orcid":"https://orcid.org/0000-0002-1394-6386"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Ghanshyam Verma","raw_affiliation_strings":["Insight Research Ireland Centre for Data Analytics, Data Science Institute, University of Galway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insight Research Ireland Centre for Data Analytics, Data Science Institute, University of Galway","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025406029","display_name":"Paul Buitelaar","orcid":"https://orcid.org/0000-0001-7238-9842"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Paul Buitelaar","raw_affiliation_strings":["Insight Research Ireland Centre for Data Analytics, Data Science Institute, University of Galway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insight Research Ireland Centre for Data Analytics, Data Science Institute, University of Galway","institution_ids":["https://openalex.org/I188760350"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5130054732"],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72179732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"46","first_page":"39285","last_page":"39293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3463999927043915,"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":0.3463999927043915,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.10559999942779541,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.07620000094175339,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6044999957084656},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5579000115394592},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.49540001153945923},{"id":"https://openalex.org/keywords/renewable-energy","display_name":"Renewable energy","score":0.45669999718666077},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3675999939441681},{"id":"https://openalex.org/keywords/energy-policy","display_name":"Energy policy","score":0.35830000042915344},{"id":"https://openalex.org/keywords/public-policy","display_name":"Public policy","score":0.3488999903202057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732699990272522},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6044999957084656},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49540001153945923},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4690999984741211},{"id":"https://openalex.org/C188573790","wikidata":"https://www.wikidata.org/wiki/Q12705","display_name":"Renewable energy","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3646000027656555},{"id":"https://openalex.org/C131046424","wikidata":"https://www.wikidata.org/wiki/Q1805337","display_name":"Energy policy","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C109986646","wikidata":"https://www.wikidata.org/wiki/Q546113","display_name":"Public policy","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3019999861717224},{"id":"https://openalex.org/C123587114","wikidata":"https://www.wikidata.org/wiki/Q2101508","display_name":"Policy analysis","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i46.41277","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i46.41277","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41277/45238","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i46.41277","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i46.41277","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41277/45238","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5330950021743774,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138921780.pdf","grobid_xml":"https://content.openalex.org/works/W7138921780.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accelerating":[0],"research":[1,172,185],"in":[2,123,137,146,173,186],"renewable":[3,50,94,188],"energy":[4,51,95,189],"policy":[5,21,52,96,160,174],"is":[6],"critical":[7],"for":[8,44,159,169,200],"addressing":[9],"climate":[10],"change":[11],"and":[12,33,60,71,112,131,140,162,175,196,202],"enabling":[13,193],"informed":[14],"decision-making.":[15],"Question":[16],"answering":[17],"(QA)":[18],"over":[19,91],"public":[20],"documents":[22],"presents":[23],"unique":[24],"challenges":[25],"due":[26],"to":[27,68],"their":[28],"legal":[29,138,201],"structure,":[30],"conditional":[31,141],"dependencies,":[32],"domain-specific":[34,82],"vocabulary.":[35],"In":[36],"this":[37,76,180],"paper,":[38],"we":[39,78],"introduce":[40],"EvalQAG,":[41],"a":[42,81,116,154,166],"framework":[43],"generating":[45],"high-quality":[46],"QA":[47,73,83,88,129,156,171,198],"pairs":[48,89],"from":[49,90],"documents.":[53,97,205],"EvalQAG":[54,152],"combines":[55],"structured":[56],"prompts,":[57],"retrieval-augmented":[58],"inputs,":[59],"multi-stage":[61],"evaluation":[62],"using":[63],"large":[64],"language":[65],"models":[66,130],"(LLMs)":[67],"support":[69],"accurate":[70],"diverse":[72],"generation.":[74],"Using":[75],"framework,":[77],"construct":[79],"REPolicyQA,":[80],"dataset":[84,99],"comprising":[85],"approximately":[86],"160,000":[87],"1,000":[92],"U.S.":[93],"The":[98],"covers":[100],"five":[101],"policy-relevant":[102],"question":[103],"types:":[104],"Yes/No,":[105],"Yes/No":[106],"with":[107],"Conditions,":[108],"Factual,":[109],"Legal":[110],"Obligation,":[111],"Descriptive,":[113],"which":[114],"capture":[115],"wide":[117],"range":[118],"of":[119],"reasoning":[120,139],"patterns":[121],"grounded":[122],"regulatory":[124,176,204],"texts.":[125],"We":[126,178],"evaluate":[127],"multiple":[128],"uncover":[132],"significant":[133],"performance":[134],"gaps,":[135],"particularly":[136,191],"inference,":[142],"highlighting":[143],"major":[144],"shortcomings":[145],"current":[147],"systems.":[148],"Our":[149],"results":[150],"establish":[151],"as":[153,165],"generalizable":[155],"generation":[157],"pipeline":[158],"texts":[161],"position":[163],"REPolicyQA":[164],"new":[167],"benchmark":[168],"advancing":[170],"domains.":[177],"believe":[179],"work":[181],"can":[182],"foster":[183],"impactful":[184],"the":[187],"sector,":[190],"by":[192],"more":[194],"robust":[195],"explainable":[197],"systems":[199],"condition-heavy":[203]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-20T00:00:00"}