{"id":"https://openalex.org/W4416036626","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.344","title":"ViLBench: A Suite for Vision-Language Process Reward Modeling","display_name":"ViLBench: A Suite for Vision-Language Process Reward Modeling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036626","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.344"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.344","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.344","pdf_url":"https://aclanthology.org/2025.emnlp-main.344.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.emnlp-main.344.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048179343","display_name":"Haoqin Tu","orcid":"https://orcid.org/0000-0002-5627-249X","observed_orcids":["https://orcid.org/0000-0002-5627-249X"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoqin Tu","raw_affiliation_strings":["Amazon Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072751690","display_name":"Weitao Feng","orcid":"https://orcid.org/0000-0003-2517-9206","observed_orcids":["https://orcid.org/0000-0003-2517-9206"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weitao Feng","raw_affiliation_strings":["Amazon Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040253516","display_name":"Hardy Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hardy Chen","raw_affiliation_strings":["Amazon Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028251167","display_name":"Hui Liu","orcid":"https://orcid.org/0000-0002-7887-7537","observed_orcids":["https://orcid.org/0000-0002-7887-7537"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Liu","raw_affiliation_strings":["Amazon Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102008510","display_name":"Xianfeng Tang","orcid":"https://orcid.org/0000-0003-1554-2761","observed_orcids":["https://orcid.org/0000-0003-1554-2761"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianfeng Tang","raw_affiliation_strings":["Amazon Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022344556","display_name":"Cihang Xie","orcid":"https://orcid.org/0000-0003-1243-8045","observed_orcids":["https://orcid.org/0000-0003-1243-8045"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cihang Xie","raw_affiliation_strings":["Amazon Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":1.5114,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86614631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6775","last_page":"6790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.00019999999494757503,"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":0.00019999999494757503,"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/process-reward-models","display_name":"process reward models","score":0.7599999904632568},{"id":"https://openalex.org/keywords/multimodal-benchmark","display_name":"multimodal benchmark","score":0.5149999856948853},{"id":"https://openalex.org/keywords/chain-of-thought","display_name":"chain-of-thought","score":0.7120000123977661},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.777999997138977},{"id":"https://openalex.org/keywords/openai-o1","display_name":"OpenAI o1","score":0.796999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5932999849319458},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C76956256","wikidata":"https://www.wikidata.org/wiki/Q27610560","display_name":"Process modeling","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.24809999763965607},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24529999494552612},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.24490000307559967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.344","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.344","pdf_url":"https://aclanthology.org/2025.emnlp-main.344.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.20271","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.20271","pdf_url":"https://arxiv.org/pdf/2503.20271","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.20271","doi":"https://doi.org/10.48550/arxiv.2503.20271","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.20271","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.344","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.344","pdf_url":"https://aclanthology.org/2025.emnlp-main.344.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036626.pdf","grobid_xml":"https://content.openalex.org/works/W4416036626.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6979280327","https://openalex.org/W4415332263","https://openalex.org/W4413145082","https://openalex.org/W4407806433","https://openalex.org/W7157125804","https://openalex.org/W7077045424","https://openalex.org/W4416039144","https://openalex.org/W4416254304","https://openalex.org/W7128536784","https://openalex.org/W7160284950"],"abstract_inverted_index":{"Process-supervised":[0],"reward":[1,55,58,63,106,134,140],"models":[2,49,59,64],"serve":[3],"as":[4,51],"a":[5,98,123],"fine-grained":[6],"function":[7],"that":[8,72],"provides":[9],"detailed":[10],"step-wise":[11],"feedback":[12],"to":[13,102,152,164,167],"model":[14,149],"responses,":[15],"facilitating":[16],"effective":[17],"selection":[18],"of":[19,54,157],"reasoning":[20],"trajectories":[21],"for":[22],"complex":[23],"tasks.Despite":[24],"its":[25,168],"advantages,":[26],"evaluation":[27],"on":[28,66,171],"PRMs":[29],"remains":[30],"less":[31],"explored,":[32],"especially":[33],"in":[34],"the":[35,128],"multimodal":[36],"domain.To":[37],"address":[38],"this":[39,41],"gap,":[40],"paper":[42],"first":[43],"benchmarks":[44],"current":[45,118],"vision":[46],"large":[47],"language":[48],"(VLLMs)":[50],"two":[52],"types":[53],"models:":[56],"output":[57],"(ORMs)":[60],"and":[61,82,133,162,183],"process":[62,105,139],"(PRMs)":[65],"multiple":[67],"vision-language":[68,99,138],"benchmarks,":[69],"which":[70],"reveal":[71],"neither":[73],"ORM":[74],"nor":[75],"PRM":[76],"consistently":[77],"outperforms":[78],"across":[79],"all":[80],"tasks,":[81],"superior":[83],"VLLMs":[84,132],"do":[85],"not":[86],"necessarily":[87],"yield":[88],"better":[89],"rewarding":[90],"performance.To":[91],"further":[92],"advance":[93],"evaluation,":[94],"we":[95,120],"introduce":[96],"VILBENCH,":[97],"benchmark":[100],"designed":[101],"require":[103],"intensive":[104],"signals.Notably,":[107],"Ope-nAI's":[108],"GPT-4o":[109],"with":[110],"Chain-of-Thought":[111],"(CoT)":[112],"achieves":[113],"only":[114],"27.3%":[115],"accuracy,":[116],"challenging":[117],"VLLMs.Lastly,":[119],"preliminarily":[121],"showcase":[122],"promising":[124],"pathway":[125],"towards":[126],"bridging":[127],"gap":[129],"between":[130],"general":[131],"models-by":[135],"collecting":[136],"73.6K":[137],"data":[141,184],"using":[142],"an":[143,154],"enhanced":[144],"treesearch":[145],"algorithm,":[146],"our":[147,180],"3B":[148],"is":[150],"able":[151],"achieve":[153],"average":[155],"improvement":[156],"3.3%":[158],"over":[159],"standard":[160],"CoT":[161],"up":[163],"2.5%":[165],"compared":[166],"untrained":[169],"counterpart":[170],"VILBENCH":[172],"by":[173],"selecting":[174],"OpenAI":[175],"o1's":[176],"generations.We":[177],"will":[178],"release":[179],"code,":[181],"model,":[182],"at":[185],"https:":[186],"//ucsc-vlaa.github.io/ViLBench.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-11-08T00:00:00"}