{"id":"https://openalex.org/W7166847040","doi":"https://doi.org/10.18653/v1/2026.acl-long.1642","title":"EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation","display_name":"EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166847040","doi":"https://doi.org/10.18653/v1/2026.acl-long.1642"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1642","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1642","pdf_url":"https://aclanthology.org/2026.acl-long.1642.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.1642.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139850233","display_name":"Pei Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei Yang","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139741065","display_name":"Wanyi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanyi Chen","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139846325","display_name":"Ke Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119027766","display_name":"Lynn Ai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lynn Ai","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139778704","display_name":"Eric Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Yang","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139762901","display_name":"Tianyu Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Shi","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.7132,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98864465,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"35513","last_page":"35529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5058000087738037,"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":0.5058000087738037,"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":0.1793999969959259,"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/T12031","display_name":"Speech and dialogue systems","score":0.06480000168085098,"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/code","display_name":"Code (set theory)","score":0.5048999786376953},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4413999915122986},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.38749998807907104},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.35409998893737793},{"id":"https://openalex.org/keywords/distributed-transaction","display_name":"Distributed transaction","score":0.3149000108242035},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27320000529289246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6456000208854675},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5048999786376953},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.35409998893737793},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C25185021","wikidata":"https://www.wikidata.org/wiki/Q4053284","display_name":"Distributed transaction","level":4,"score":0.3149000108242035},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C47434764","wikidata":"https://www.wikidata.org/wiki/Q1770035","display_name":"Dead code","level":5,"score":0.27140000462532043},{"id":"https://openalex.org/C11354467","wikidata":"https://www.wikidata.org/wiki/Q953487","display_name":"Transaction processing system","level":4,"score":0.26989999413490295},{"id":"https://openalex.org/C72108876","wikidata":"https://www.wikidata.org/wiki/Q844565","display_name":"Transaction processing","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1642","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1642","pdf_url":"https://aclanthology.org/2026.acl-long.1642.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.1642","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1642","pdf_url":"https://aclanthology.org/2026.acl-long.1642.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166847040.pdf","grobid_xml":"https://content.openalex.org/works/W7166847040.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,99],"are":[3,48,55],"increasingly":[4],"applied":[5],"to":[6],"various":[7],"development":[8],"scenarios.However,":[9],"in":[10],"on-chain":[11],"transaction":[12],"scenarios,":[13],"even":[14],"a":[15,85],"minor":[16],"error":[17],"can":[18],"cause":[19],"irreversible":[20],"loss":[21],"for":[22,36],"users.Existing":[23],"evaluations":[24],"often":[25],"overlook":[26],"execution":[27],"accuracy":[28],"and":[29,60,105,119],"safety.We":[30],"introduce":[31],"EVM-QuestBench,":[32],"an":[33],"execution-grounded":[34],"benchmark":[35,43],"natural-language":[37],"transaction-script":[38],"generation":[39],"on":[40,84],"EVM-compatible":[41],"chains.The":[42],"employs":[44],"dynamic":[45],"evaluation:":[46],"instructions":[47],"sampled":[49],"from":[50,57],"template":[51],"pools,":[52],"numeric":[53],"parameters":[54],"drawn":[56],"predefined":[58],"intervals,":[59],"validators":[61],"verify":[62],"outcomes":[63],"against":[64],"these":[65],"instantiated":[66],"values.EVM-QuestBench":[67],"contains":[68],"107":[69],"tasks":[70,93],"(62":[71],"atomic,":[72],"45":[73],"composite).Its":[74],"modular":[75],"architecture":[76],"enables":[77],"rapid":[78],"task":[79],"development.The":[80],"runner":[81],"executes":[82],"scripts":[83],"forked":[86],"EVM":[87],"chain":[88],"with":[89,100,110],"snapshot":[90],"isolation;":[91],"composite":[92],"apply":[94],"step-efficiency":[95],"decay.We":[96],"evaluate":[97],"20":[98],"5":[101],"independent":[102],"rounds":[103],"each":[104],"find":[106],"large":[107],"performance":[108],"gaps,":[109],"split":[111],"scores":[112],"revealing":[113],"persistent":[114],"asymmetry":[115],"between":[116],"single-action":[117],"precision":[118],"multi-step":[120],"workflow":[121],"completion.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-07-02T00:00:00"}