{"id":"https://openalex.org/W4399795393","doi":"https://doi.org/10.1145/3637528.3671564","title":"R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models","display_name":"R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4399795393","doi":"https://doi.org/10.1145/3637528.3671564"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671564","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671564","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070578353","display_name":"Shangqing Tu","orcid":"https://orcid.org/0009-0008-0640-3413"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangqing Tu","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106457977","display_name":"Yuanchun Wang","orcid":"https://orcid.org/0009-0008-3708-1381"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"funder","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchun Wang","raw_affiliation_strings":["SoI, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SoI, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038246814","display_name":"Jifan Yu","orcid":"https://orcid.org/0000-0003-3430-4048"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jifan Yu","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113412411","display_name":"Yuyang Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Xie","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101240636","display_name":"Yaran Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"funder","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaran Shi","raw_affiliation_strings":["SIOE, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SIOE, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775958","display_name":"Xiaozhi Wang","orcid":"https://orcid.org/0000-0002-5727-143X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaozhi Wang","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104289975","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-3633-485X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"funder","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["SoI, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SoI, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060498828","display_name":"Lei Hou","orcid":"https://orcid.org/0000-0002-8907-3526"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Hou","raw_affiliation_strings":["BNRist, DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"BNRist, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003324011","display_name":"Juanzi Li","orcid":"https://orcid.org/0000-0002-6244-0664"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juanzi Li","raw_affiliation_strings":["BNRist, DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"BNRist, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":78},"biblio":{"volume":null,"issue":null,"first_page":"5813","last_page":"5824"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9999,"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":0.9999,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9978,"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/T13629","display_name":"Text Readability and Simplification","score":0.9725,"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/python","display_name":"Python","score":0.722393},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.41339043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.859699},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.83501387},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.722393},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.64991605},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5890108},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.54552},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4473641},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.41339043},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3978148},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39444423},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33182818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33030224},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17731926},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671564","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671564","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2406.11681","pdf_url":"https://arxiv.org/pdf/2406.11681","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671564","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671564","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.51}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":15,"referenced_works":["https://openalex.org/W2022322548","https://openalex.org/W2072927260","https://openalex.org/W2251818205","https://openalex.org/W2952179106","https://openalex.org/W2962985038","https://openalex.org/W3027879771","https://openalex.org/W3190126809","https://openalex.org/W4285147034","https://openalex.org/W4306176157","https://openalex.org/W4322708560","https://openalex.org/W4385571271","https://openalex.org/W4385573083","https://openalex.org/W4387426216","https://openalex.org/W4389518608","https://openalex.org/W4389519118"],"related_works":["https://openalex.org/W829257147","https://openalex.org/W4393677513","https://openalex.org/W4390832911","https://openalex.org/W4385302116","https://openalex.org/W4205140848","https://openalex.org/W3204758414","https://openalex.org/W2978678743","https://openalex.org/W2797837731","https://openalex.org/W2549786917","https://openalex.org/W2068663075"],"abstract_inverted_index":{"Large":[0,22],"language":[1],"models":[2],"have":[3],"achieved":[4],"remarkable":[5],"success":[6],"on":[7,44,102],"general":[8],"NLP":[9],"tasks,":[10],"but":[11],"they":[12],"may":[13],"fall":[14],"short":[15],"for":[16,95],"domain-specific":[17],"problems.":[18],"Recently,":[19],"various":[20,45],"Retrieval-Augmented":[21],"Language":[23],"Models":[24],"(RALLMs)":[25],"are":[26,163],"proposed":[27],"to":[28,73,108,165,172],"address":[29,58],"this":[30,55],"shortcoming.":[31],"However,":[32],"existing":[33],"evaluation":[34,76,117],"tools":[35],"only":[36],"provide":[37],"a":[38,69,156],"few":[39],"baselines":[40],"and":[41,93,112,125,140,151,159,177],"evaluate":[42],"them":[43],"domains":[46],"without":[47],"mining":[48],"the":[49,59,66,75,96,103,133,145,175,178],"depth":[50],"of":[51,61,77,98,118,135,147],"domain":[52,152],"knowledge.":[53],"In":[54],"paper,":[56],"we":[57],"challenges":[60],"evaluating":[62],"RALLMs":[63,120,136],"by":[64],"introducing":[65],"R-Eval":[67],"toolkit,":[68,86],"Python":[70],"toolkit":[71],"designed":[72,107],"streamline":[74],"different":[78,138],"RAG":[79,91,157],"workflows":[80,92],"in":[81,132],"conjunction":[82],"with":[83],"LLMs.":[84],"Our":[85,142],"which":[87],"supports":[88],"popular":[89],"built-in":[90],"allows":[94],"incorporation":[97],"customized":[99],"testing":[100],"data":[101],"specific":[104],"domain,":[105],"is":[106],"be":[109],"user-friendly,":[110],"modular,":[111],"extensible.":[113],"We":[114,162],"conduct":[115],"an":[116],"21":[119],"across":[121,137],"three":[122],"task":[123,150],"levels":[124],"two":[126],"representative":[127],"domains,":[128],"revealing":[129],"significant":[130],"variations":[131],"effectiveness":[134],"tasks":[139],"domains.":[141],"analysis":[143],"emphasizes":[144],"importance":[146],"considering":[148],"both":[149,174],"requirements":[153],"when":[154],"choosing":[155],"workflow":[158],"LLM":[160],"combination.":[161],"committed":[164],"continuously":[166],"maintaining":[167],"our":[168],"platform":[169],"at":[170],"https://github.com/THU-KEG/R-Eval":[171],"facilitate":[173],"industry":[176],"researchers.":[179]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4399795393","counts_by_year":[],"updated_date":"2025-04-06T00:17:43.257223","created_date":"2024-06-19"}