{"id":"https://openalex.org/W4416004014","doi":"https://doi.org/10.1145/3731599.3767410","title":"Automated MCQA Benchmarking at Scale: Evaluating Reasoning Traces as Retrieval Sources for Domain Adaptation of Small Language Models","display_name":"Automated MCQA Benchmarking at Scale: Evaluating Reasoning Traces as Retrieval Sources for Domain Adaptation of Small Language Models","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004014","doi":"https://doi.org/10.1145/3731599.3767410"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767410","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767410","pdf_url":null,"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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767410","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015717928","display_name":"Ozan G\u00f6kdemir","orcid":"https://orcid.org/0000-0001-5299-1983"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ozan Gokdemir","raw_affiliation_strings":["Department of Computer Science, University of Chicago, Chicago, IL, USA and Data Science and Learning Division, Argonne National Laboratory (ANL), Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0001-5299-1983","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Chicago, Chicago, IL, USA and Data Science and Learning Division, Argonne National Laboratory (ANL), Chicago, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045490083","display_name":"Neil Getty","orcid":"https://orcid.org/0000-0003-0535-8362"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil Getty","raw_affiliation_strings":["Data Science and Learning Division, Argonne National Laboratory (ANL), Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-0535-8362","affiliations":[{"raw_affiliation_string":"Data Science and Learning Division, Argonne National Laboratory (ANL), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056940311","display_name":"Robert Underwood","orcid":"https://orcid.org/0000-0002-1464-729X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Underwood","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory (ANL), Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-1464-729X","affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory (ANL), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004608167","display_name":"Sandeep Madireddy","orcid":"https://orcid.org/0000-0002-0437-8655"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Madireddy","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory (ANL), Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-0437-8655","affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory (ANL), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory (ANL), Lemont, USA"],"raw_orcid":"https://orcid.org/0000-0002-7890-3934","affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory (ANL), Lemont, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028188095","display_name":"Arvind Ramanathan","orcid":"https://orcid.org/0000-0002-1622-5488"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Ramanathan","raw_affiliation_strings":["Data Science and Learning Division, Argonne National Laboratory (ANL), Lemont, IL, USA and Department of Computer Science, University of Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-1622-5488","affiliations":[{"raw_affiliation_string":"Data Science and Learning Division, Argonne National Laboratory (ANL), Lemont, IL, USA and Department of Computer Science, University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian T. Foster","raw_affiliation_strings":["Data Science and Learning Division, Argonne National Laboratory (ANL), Lemont, IL, USA and Department of Computer Science, University of Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-2129-5269","affiliations":[{"raw_affiliation_string":"Data Science and Learning Division, Argonne National Laboratory (ANL), Lemont, IL, USA and Department of Computer Science, University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053682943","display_name":"Rick Stevens","orcid":"https://orcid.org/0000-0002-4268-4020"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rick L. Stevens","raw_affiliation_strings":["Data Science and Learning Division, Argonne National Laboratory (ANL), Lemont, IL, USA and Department of Computer Science, University of Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-4268-4020","affiliations":[{"raw_affiliation_string":"Data Science and Learning Division, Argonne National Laboratory (ANL), Lemont, IL, USA and Department of Computer Science, University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29154809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"545","last_page":"552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.586899995803833,"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":0.586899995803833,"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":0.19179999828338623,"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":0.03290000185370445,"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/pipeline","display_name":"Pipeline (software)","score":0.6546000242233276},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5978000164031982},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5372999906539917},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5339000225067139},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.527899980545044},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5185999870300293},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4311000108718872},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.396699994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998999953269958},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5978000164031982},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.527899980545044},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4887999892234802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4645000100135803},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3278000056743622},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3140999972820282},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2705000042915344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767410","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767410","pdf_url":null,"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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767410","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767410","pdf_url":null,"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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2479527281","https://openalex.org/W2943761765","https://openalex.org/W2970482702","https://openalex.org/W3046375318","https://openalex.org/W4402906968","https://openalex.org/W4403753476","https://openalex.org/W4411490478","https://openalex.org/W4415124086"],"related_works":[],"abstract_inverted_index":{"As":[0,63],"scientific":[1,43],"knowledge":[2],"grows":[3],"at":[4],"an":[5],"unprecedented":[6],"pace,":[7],"evaluation":[8],"benchmarks":[9,37],"must":[10],"evolve":[11],"to":[12,132],"reflect":[13],"new":[14],"discoveries":[15],"and":[16,60,79,107,125,140],"ensure":[17],"language":[18,89],"models":[19,90,131],"are":[20],"tested":[21],"on":[22,93,122,135],"current,":[23],"diverse":[24],"literature.":[25],"We":[26,82,114],"propose":[27],"a":[28,64,85],"scalable,":[29],"modular":[30],"framework":[31],"for":[32],"generating":[33],"multiple-choice":[34],"question-answering":[35],"(MCQA)":[36],"directly":[38],"from":[39,73,103,108,112],"large":[40],"corpora":[41],"of":[42,50,87],"papers.":[44],"Our":[45],"pipeline":[46],"automates":[47],"every":[48],"stage":[49],"MCQA":[51],"creation,":[52],"including":[53],"PDF":[54],"parsing,":[55],"semantic":[56,105],"chunking,":[57],"question":[58],"generation,":[59],"model":[61],"evaluation.":[62],"case":[65],"study,":[66],"we":[67],"generate":[68],"more":[69],"than":[70],"16,000":[71],"MCQs":[72],"22,000":[74],"open-access":[75],"articles":[76],"in":[77],"radiation":[78],"cancer":[80],"biology.":[81],"then":[83],"evaluate":[84],"suite":[86],"small":[88,130],"(1.1B\u201314B":[91],"parameters)":[92],"these":[94],"questions,":[95],"comparing":[96],"baseline":[97],"accuracy":[98],"with":[99],"retrieval-augmented":[100],"generation":[101],"(RAG)":[102],"paper-derived":[104],"chunks":[106],"reasoning":[109],"traces":[110],"distilled":[111],"GPT-4.1.":[113],"find":[115],"that":[116],"reasoning-trace":[117],"retrieval":[118],"consistently":[119],"improves":[120],"performance":[121],"both":[123],"synthetic":[124],"expert-annotated":[126],"benchmarks,":[127],"enabling":[128],"several":[129],"surpass":[133],"GPT-4":[134],"the":[136],"2023":[137],"Astro":[138],"Radiation":[139],"Cancer":[141],"Biology":[142],"exam.":[143]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-07T00:00:00"}