{"id":"https://openalex.org/W7151220081","doi":"https://doi.org/10.1109/icmla66185.2025.00064","title":"Attr-RAG: Attribution-Guided Retrieval-Augmented Generation for Scientific Experiment Design","display_name":"Attr-RAG: Attribution-Guided Retrieval-Augmented Generation for Scientific Experiment Design","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7151220081","doi":"https://doi.org/10.1109/icmla66185.2025.00064"},"language":null,"primary_location":{"id":"doi:10.1109/icmla66185.2025.00064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066316078","display_name":"Fazle Rahat","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fazle Rahat","raw_affiliation_strings":["University of Central Florida,Orlando,FL"],"affiliations":[{"raw_affiliation_string":"University of Central Florida,Orlando,FL","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133120559","display_name":"M Shifat Hossain","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M Shifat Hossain","raw_affiliation_strings":["University of Central Florida,Orlando,FL"],"affiliations":[{"raw_affiliation_string":"University of Central Florida,Orlando,FL","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104159425","display_name":"Arvind Ramanathan","orcid":null},"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":["Argonne National Laboratory,Lemont,IL"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory,Lemont,IL","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072303405","display_name":"S. K. Jha","orcid":"https://orcid.org/0000-0003-4853-6085"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumit Jha","raw_affiliation_strings":["University of Florida,Gainesville,FL"],"affiliations":[{"raw_affiliation_string":"University of Florida,Gainesville,FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133075867","display_name":"Hao Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Zheng","raw_affiliation_strings":["University of Central Florida,Orlando,FL"],"affiliations":[{"raw_affiliation_string":"University of Central Florida,Orlando,FL","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014892277","display_name":"Rickard Ewetz","orcid":"https://orcid.org/0000-0002-4183-6926"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rickard Ewetz","raw_affiliation_strings":["University of Florida,Gainesville,FL"],"affiliations":[{"raw_affiliation_string":"University of Florida,Gainesville,FL","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5066316078"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87271419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"424","last_page":"431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.19040000438690186,"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":0.19040000438690186,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.17569999396800995,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.06270000338554382,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.27239999175071716},{"id":"https://openalex.org/keywords/design-of-experiments","display_name":"Design of experiments","score":0.26739999651908875},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2345999926328659},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.20999999344348907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3880999982357025},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.384799987077713},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C34559072","wikidata":"https://www.wikidata.org/wiki/Q2334061","display_name":"Design of experiments","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2345999926328659},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.21870000660419464},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.21719999611377716},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.20999999344348907},{"id":"https://openalex.org/C31352089","wikidata":"https://www.wikidata.org/wiki/Q3750474","display_name":"Systems design","level":2,"score":0.20589999854564667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla66185.2025.00064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W2052042865","https://openalex.org/W2112724747","https://openalex.org/W2114804859","https://openalex.org/W2921963218","https://openalex.org/W2962858109","https://openalex.org/W2970641574","https://openalex.org/W4393161188","https://openalex.org/W4402672112","https://openalex.org/W4404781754"],"related_works":[],"abstract_inverted_index":{"Evidence-based":[0],"science":[1],"depends":[2],"on":[3,134],"the":[4,22,53,152,187,212],"iterative":[5],"integration":[6],"of":[7,24,30,56,102,180,186,216],"experimentation,":[8],"a":[9,139],"process":[10],"traditionally":[11],"driven":[12],"by":[13,71,202],"slow":[14],"and":[15,100,121,168,190,209,219],"error-prone":[16],"human":[17],"effort.":[18],"This":[19,155],"has":[20],"inspired":[21],"vision":[23],"an":[25,111],"automated":[26],"\"robot":[27],"scientist\"":[28],"capable":[29],"conducting":[31],"end-to-end":[32],"experimentation.":[33],"While":[34],"Large":[35],"Language":[36],"Models":[37],"(LLMs)":[38],"can":[39],"generate":[40],"procedural":[41],"instructions,":[42],"they":[43],"often":[44],"struggle":[45],"to":[46,52,74,94,115,145],"accurately":[47],"describe":[48],"scientific":[49,90],"experiments":[50],"due":[51,93],"limited":[54],"availability":[55],"high-quality,":[57],"domain-specific":[58],"examples":[59],"in":[60,177],"their":[61],"training":[62],"data.":[63],"Retrieval-Augmented":[64],"Generation":[65],"(RAG)":[66],"helps":[67],"bridge":[68],"this":[69,106],"gap":[70],"allowing":[72],"LLMs":[73],"access":[75],"up-to-date":[76],"external":[77],"information.":[78,104,126],"However,":[79],"despite":[80],"being":[81],"effective":[82],"for":[83,166],"short":[84],"questions,":[85],"RAG":[86,113,129],"struggles":[87],"with":[88],"long-form":[89],"experimental":[91],"queries":[92],"information":[95],"loss":[96],"from":[97],"chunk":[98],"fragmentation":[99],"retrieval":[101],"irrelevant":[103,117],"In":[105,198],"paper,":[107],"we":[108],"propose":[109],"Attr-RAG,":[110],"attribution-guided":[112,156],"framework":[114],"remove":[116],"or":[118],"misleading":[119],"context":[120],"retaining":[122],"only":[123,160],"complete,":[124],"relevant":[125],"Unlike":[127],"traditional":[128],"methods":[130],"that":[131,159],"rely":[132],"solely":[133],"vector":[135],"similarity,":[136],"Attr-RAG":[137,173],"introduces":[138],"refinement":[140],"stage":[141],"using":[142],"occlusion-based":[143],"attribution":[144],"identify":[146],"which":[147],"retrieved":[148],"chunks":[149,163],"truly":[150],"influence":[151],"LLM\u2019s":[153],"response.":[154],"filtering":[157],"ensures":[158],"contextually":[161],"coherent":[162],"are":[164],"used":[165],"accurate":[167],"grounded":[169],"final":[170],"answer":[171],"generation.":[172],"demonstrated":[174],"superior":[175],"performance":[176],"9":[178],"out":[179],"10":[181],"chemistry":[182],"lab":[183],"experiment":[184],"tasks":[185],"ChemEx":[188],"dataset":[189],"outperformed":[191],"baselines":[192],"across":[193,224],"most":[194],"quantitative":[195],"evaluation":[196,227],"metrics.":[197],"qualitative":[199],"evaluations":[200],"conducted":[201],"state-of-the-art":[203],"LLM":[204],"judges":[205],"(GPT-4o,":[206],"Gemini":[207],"2.5,":[208],"Grok":[210],"3),":[211],"top":[213],"mean":[214],"scores":[215],"27.8,":[217],"27.1,":[218],"22.9,":[220],"respectively,":[221],"were":[222],"achieved":[223],"six":[225],"key":[226],"criteria.":[228]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-04-08T00:00:00"}