{"id":"https://openalex.org/W4412888077","doi":"https://doi.org/10.18653/v1/2025.findings-acl.877","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","display_name":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888077","doi":"https://doi.org/10.18653/v1/2025.findings-acl.877"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.877","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.877","pdf_url":"https://aclanthology.org/2025.findings-acl.877.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.877.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102626155","display_name":"Zhuoran Jin","orcid":"https://orcid.org/0000-0002-1667-8145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuoran Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066961275","display_name":"Hongbang Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongbang Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013651593","display_name":"Tianyi Men","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Men","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101759357","display_name":"Pengfei Cao","orcid":"https://orcid.org/0000-0003-4443-1892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101939526","display_name":"Yubo Chen","orcid":"https://orcid.org/0000-0002-9862-4094"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yubo Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004171626","display_name":"Jiexin Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiexin Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044031066","display_name":"Huaijun Li","orcid":"https://orcid.org/0000-0001-9493-0660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaijun Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076858450","display_name":"Xiaojian Jiang","orcid":"https://orcid.org/0000-0001-7192-5420"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojian Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389900","display_name":"Kang Liu","orcid":"https://orcid.org/0000-0002-6083-8433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058685565","display_name":"Jun Zhao","orcid":"https://orcid.org/0000-0002-3539-2249"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhao","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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17061","last_page":"17090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9004999995231628,"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/benchmarking","display_name":"Benchmarking","score":0.8185354471206665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6563292145729065},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6269054412841797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45410996675491333},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3644172251224518},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1097126305103302},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1082310676574707},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.08740973472595215}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8185354471206665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6563292145729065},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6269054412841797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45410996675491333},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3644172251224518},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1097126305103302},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1082310676574707},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.08740973472595215},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.877","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.877","pdf_url":"https://aclanthology.org/2025.findings-acl.877.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.877","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.877","pdf_url":"https://aclanthology.org/2025.findings-acl.877.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5208670511","display_name":null,"funder_award_id":"U24A20335","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888077.pdf","grobid_xml":"https://content.openalex.org/works/W4412888077.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699"],"abstract_inverted_index":{"Despite":[0],"the":[1,29,67,109,134,166],"significant":[2],"progress":[3],"made":[4],"by":[5],"existing":[6,155],"retrieval":[7],"augmented":[8],"language":[9],"models":[10,33],"(RALMs)":[11],"in":[12,18,60,73,148,162],"providing":[13],"trustworthy":[14],"responses":[15],"and":[16,52,80,94,104,124,144],"grounding":[17],"reliable":[19,55],"sources,":[20],"they":[21],"often":[22],"overlook":[23],"effective":[24],"alignment":[25,30,59],"with":[26,130],"human":[27,41,131],"preferences.In":[28],"process,":[31],"reward":[32],"(RMs)":[34],"act":[35],"as":[36],"a":[37,54,127,138,169],"crucial":[38,79],"proxy":[39],"for":[40,57,70,168],"values":[42],"to":[43,50,84,107,119],"guide":[44],"optimization.However,":[45],"it":[46],"remains":[47],"unclear":[48],"how":[49],"evaluate":[51],"select":[53],"RM":[56],"preference":[58,121,163],"RALMs.To":[61],"this":[62],"end,":[63],"we":[64,76,97,114,136,151],"propose":[65],"RAG-RewardBench,":[66,135],"first":[68],"benchmark":[69],"evaluating":[71],"RMs":[72,143],"RAG":[74,100,149],"settings.First,":[75],"design":[77],"four":[78],"challenging":[81],"RAG-specific":[82],"scenarios":[83],"assess":[85],"RMs,":[86],"including":[87],"multi-hop":[88],"reasoning,":[89],"fine-grained":[90],"citation,":[91],"appropriate":[92],"abstain,":[93],"conflict":[95],"robustness.Then,":[96],"incorporate":[98],"18":[99],"subsets,":[101],"six":[102],"retrievers,":[103],"24":[105],"RALMs":[106,157],"increase":[108],"diversity":[110],"of":[111,141],"data":[112],"sources.Finally,":[113],"adopt":[115],"an":[116],"LLMas-a-judge":[117],"approach":[118],"improve":[120],"annotation":[122],"efficiency":[123],"effectiveness,":[125],"exhibiting":[126],"strong":[128],"correlation":[129],"annotations.Based":[132],"on":[133],"conduct":[137],"comprehensive":[139],"evaluation":[140],"45":[142],"uncover":[145],"their":[146],"limitations":[147],"scenarios.Additionally,":[150],"also":[152],"reveal":[153],"that":[154],"trained":[156],"show":[158],"almost":[159],"no":[160],"improvement":[161],"alignment,":[164],"highlighting":[165],"need":[167],"shift":[170],"towards":[171],"preference-aligned":[172],"training.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}