{"id":"https://openalex.org/W7224646972","doi":"https://doi.org/10.18653/2026.emnlp-main.660","title":"MelonBench: A Benchmark for Coded Entity Resolution over Noisy Web Evidence","display_name":"MelonBench: A Benchmark for Coded Entity Resolution over Noisy Web Evidence","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224646972","doi":"https://doi.org/10.18653/2026.emnlp-main.660"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.660","doi":"https://doi.org/10.18653/2026.emnlp-main.660","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.660","pdf_url":"https://aclanthology.org/2026.emnlp-main.660.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.660.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160078092","display_name":"Zhishan Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhishan Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160148681","display_name":"Jingxiao Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270671","display_name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education","ror":"https://ror.org/014zgy308","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405270671"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxiao Li","raw_affiliation_strings":["\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China","institution_ids":["https://openalex.org/I4405270671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160148074","display_name":"Yanbing Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270671","display_name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education","ror":"https://ror.org/014zgy308","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405270671"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbing Zhang","raw_affiliation_strings":["\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China","institution_ids":["https://openalex.org/I4405270671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114847758","display_name":"Liu Ziyan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270671","display_name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education","ror":"https://ror.org/014zgy308","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405270671"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyan Liu","raw_affiliation_strings":["\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China","institution_ids":["https://openalex.org/I4405270671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128709931","display_name":"Yuqing Shao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270671","display_name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education","ror":"https://ror.org/014zgy308","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405270671"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing Shao","raw_affiliation_strings":["\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China","institution_ids":["https://openalex.org/I4405270671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114243914","display_name":"Yunfei Tong","orcid":"https://orcid.org/0009-0005-0324-1074","observed_orcids":["https://orcid.org/0009-0005-0324-1074"]},"institutions":[{"id":"https://openalex.org/I4405270671","display_name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education","ror":"https://ror.org/014zgy308","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405270671"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfei Tong","raw_affiliation_strings":["\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China","institution_ids":["https://openalex.org/I4405270671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139719470","display_name":"Ganghao Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270671","display_name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education","ror":"https://ror.org/014zgy308","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405270671"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ganghao Liu","raw_affiliation_strings":["\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China","institution_ids":["https://openalex.org/I4405270671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160080795","display_name":"Qian Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering , East China University of Science and Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , East China University of Science and Technology , China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160127414","display_name":"Zhe Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270671","display_name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education","ror":"https://ror.org/014zgy308","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405270671"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u22c4 Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education , China","institution_ids":["https://openalex.org/I4405270671"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92763791,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15202","last_page":"15233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9307000041007996,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9307000041007996,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.04809999838471413,"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":0.003000000026077032,"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/entity-resolution","display_name":"entity resolution","score":0.9190000295639038},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.531000018119812},{"id":"https://openalex.org/keywords/web-data-quality","display_name":"web data quality","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.671999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5461999773979187},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4083999991416931},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.323199987411499},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.emnlp-main.660","doi":"https://doi.org/10.18653/2026.emnlp-main.660","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.660","pdf_url":"https://aclanthology.org/2026.emnlp-main.660.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.660","doi":"https://doi.org/10.18653/2026.emnlp-main.660","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.660","pdf_url":"https://aclanthology.org/2026.emnlp-main.660.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224646972.pdf","grobid_xml":"https://content.openalex.org/works/W7224646972.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3029917925","https://openalex.org/W2810777811","https://openalex.org/W2965937095","https://openalex.org/W2584987402","https://openalex.org/W2970069267","https://openalex.org/W7131859866","https://openalex.org/W7072050144","https://openalex.org/W6991764931","https://openalex.org/W160963573","https://openalex.org/W2807685814"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,98],"(LLMs)":[3],"are":[4],"increasingly":[5],"deployed":[6],"as":[7,123],"web-browsing":[8],"agents,":[9],"yet":[10],"current":[11],"benchmarks":[12],"mostly":[13],"evaluate":[14],"explicit":[15],"queries":[16],"over":[17,30],"clean":[18],"factual":[19],"evidence.We":[20],"introduce":[21],"MelonBench,":[22],"a":[23,64,146,150],"665-item":[24],"benchmark":[25,60],"for":[26,154],"coded":[27],"entity":[28,121],"resolution":[29],"noisy":[31,161],"openweb":[32],"user-generated":[33],"content,":[34],"instantiated":[35],"with":[36,68,99],"mid-to-long-tail":[37],"public":[38],"figures":[39],"in":[40],"Chinese":[41],"entertainment":[42,144],"blind-item":[43],"discourse.Solving":[44],"MelonBench":[45],"requires":[46],"agents":[47,156],"to":[48],"decode":[49],"obfuscated":[50],"clues,":[51],"retrieve":[52],"fragmented":[53],"evidence,":[54],"and":[55,75,87,100,119,126,160],"identify":[56,116],"the":[57,80,88,96],"target":[58],"entity.The":[59],"is":[61],"constructed":[62],"through":[63],"five-stage":[65],"semi-automatic":[66],"pipeline":[67],"atomic":[69],"event":[70],"stratification,":[71],"adversarial":[72],"faithfulness":[73],"auditing,":[74],"expert":[76],"verification.Across":[77],"30":[78],"systems,":[79],"best":[81,89],"non-search":[82],"model":[83],"reaches":[84,92],"25.1%":[85],"accuracy":[86],"search-enabled":[90],"system":[91],"49.9%.Controlled":[93],"comparisons":[94],"of":[95,141],"same":[97],"without":[101],"web":[102,108],"search":[103,130,155],"confirm":[104],"consistent":[105],"gains":[106],"from":[107],"search,":[109],"but":[110],"also":[111],"substantial":[112],"remaining":[113],"headroom.Diagnostic":[114],"experiments":[115],"semantic":[117],"de-obfuscation":[118],"openended":[120],"recall":[122],"key":[124],"bottlenecks,":[125],"show":[127],"that":[128],"reasoning-centric":[129],"can":[131],"outperform":[132],"report-oriented":[133],"agents.An":[134],"80-item":[135],"finance":[136],"pilot":[137],"provides":[138],"preliminary":[139],"evidence":[140],"transfer":[142],"beyond":[143],"within":[145],"Chinese-language":[147],"setting.MelonBench":[148],"offers":[149],"challenging":[151],"initial":[152],"testbed":[153],"under":[157],"intentional":[158],"obfuscation":[159],"evidence.":[162]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-30T00:00:00"}