{"id":"https://openalex.org/W7166888181","doi":"https://doi.org/10.18653/v1/2026.acl-long.535","title":"WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics","display_name":"WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166888181","doi":"https://doi.org/10.18653/v1/2026.acl-long.535"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.535","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.535","pdf_url":"https://aclanthology.org/2026.acl-long.535.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.535.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139777959","display_name":"Chenxu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenxu Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139847703","display_name":"Yingjie Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingjie Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139718008","display_name":"Wei Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139735409","display_name":"Ying Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139761385","display_name":"Tao Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Xie","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82509506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11632","last_page":"11666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.2249000072479248,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.2249000072479248,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.12080000340938568,"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/T12601","display_name":"Web Applications and Data Management","score":0.10899999737739563,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6740000247955322},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4422000050544739},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3109000027179718},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2865999937057495}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6740000247955322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6498000025749207},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42179998755455017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.535","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.535","pdf_url":"https://aclanthology.org/2026.acl-long.535.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.535","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.535","pdf_url":"https://aclanthology.org/2026.acl-long.535.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1365171213","display_name":null,"funder_award_id":"U25A6023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6317451256","display_name":null,"funder_award_id":"92464301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7957610226","display_name":null,"funder_award_id":"JYB2025XDXM118","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/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320321570","display_name":"China National Petroleum Corporation","ror":"https://ror.org/05269d038"},{"id":"https://openalex.org/F4320321851","display_name":"Fudan University","ror":"https://ror.org/013q1eq08"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166888181.pdf","grobid_xml":"https://content.openalex.org/works/W7166888181.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Web":[0],"applications":[1],"(web":[2],"apps)":[3],"have":[4],"become":[5],"a":[6,24,150,154],"key":[7],"arena":[8],"for":[9,26,36,68,102,142,153],"large":[10],"language":[11],"models":[12,148],"(LLMs)":[13],"to":[14,33,115,145],"demonstrate":[15],"their":[16,147],"code":[17],"generation":[18],"capabilities":[19],"and":[20,51,65,80,99,106,124],"commercial":[21],"potential.However,":[22],"building":[23],"benchmark":[25,67],"LLM-generated":[27],"web":[28,69],"apps":[29],"remains":[30],"challenging":[31],"due":[32],"the":[34,61,97],"need":[35],"realworld":[37],"user":[38,75,86],"requirements,":[39,76],"generalized":[40],"evaluation":[41,53,91,137],"metrics":[42,92,114],"without":[43],"relying":[44],"on":[45],"ground-truth":[46],"implementations":[47],"or":[48],"test":[49],"cases,":[50],"interpretable":[52,66,117],"results.To":[54],"address":[55],"these":[56],"challenges,":[57],"we":[58],"introduce":[59],"WebCoderBench,":[60],"first":[62],"realworld,":[63],"generalized,":[64],"app":[70],"generation.WebCoderBench":[71],"comprises":[72],"1,572":[73],"real":[74],"covering":[77],"diverse":[78],"modalities":[79],"expression":[81],"styles":[82],"that":[83,129],"reflect":[84],"realistic":[85],"intentions.Web-CoderBench":[87],"provides":[88],"24":[89],"fine-grained":[90],"across":[93,120,135],"9":[94],"perspectives,":[95],"combining":[96],"rule-based":[98],"LLM-as-a-judge":[100],"paradigms":[101],"fully":[103],"automated,":[104],"objective,":[105],"general":[107],"evaluation.Moreover,":[108],"WebCoderBench":[109],"adopts":[110],"human-preference-aligned":[111],"weights":[112],"over":[113],"yield":[116],"overall":[118],"scores.Experiments":[119],"12":[121],"representative":[122],"LLMs":[123],"2":[125],"LLM-based":[126],"agents":[127],"show":[128],"there":[130],"exists":[131],"no":[132],"dominant":[133],"model":[134],"all":[136],"metrics,":[138],"offering":[139],"an":[140],"opportunity":[141],"LLM":[143],"developers":[144],"optimize":[146],"in":[149],"targeted":[151],"manner":[152],"more":[155],"powerful":[156],"version.":[157]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}