{"id":"https://openalex.org/W4416036542","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.640","title":"Evaluating LLM-Generated Diagrams as Graphs","display_name":"Evaluating LLM-Generated Diagrams as Graphs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036542","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.640"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.640","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.640","pdf_url":"https://aclanthology.org/2025.emnlp-main.640.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.640.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120309093","display_name":"Chumeng Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chumeng Liang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003491365","display_name":"Jiaxuan You","orcid":"https://orcid.org/0000-0003-1812-7598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxuan You","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120309093"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35533416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12689","last_page":"12701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.20059999823570251,"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":0.20059999823570251,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.09839999675750732,"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":0.0925000011920929,"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/leverage","display_name":"Leverage (statistics)","score":0.6453999876976013},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5802000164985657},{"id":"https://openalex.org/keywords/diagram","display_name":"Diagram","score":0.5781000256538391},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49559998512268066},{"id":"https://openalex.org/keywords/class-diagram","display_name":"Class diagram","score":0.490200012922287},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.47119998931884766},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.43540000915527344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672000288963318},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6453999876976013},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5802000164985657},{"id":"https://openalex.org/C186399060","wikidata":"https://www.wikidata.org/wiki/Q959962","display_name":"Diagram","level":2,"score":0.5781000256538391},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C202446494","wikidata":"https://www.wikidata.org/wiki/Q664166","display_name":"Class diagram","level":4,"score":0.490200012922287},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C168054591","wikidata":"https://www.wikidata.org/wiki/Q17152869","display_name":"Story-driven modeling","level":5,"score":0.37380000948905945},{"id":"https://openalex.org/C153185123","wikidata":"https://www.wikidata.org/wiki/Q1391624","display_name":"Sequence diagram","level":4,"score":0.34850001335144043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C161756209","wikidata":"https://www.wikidata.org/wiki/Q613423","display_name":"Use Case Diagram","level":5,"score":0.29829999804496765},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C20837028","wikidata":"https://www.wikidata.org/wiki/Q623966","display_name":"Influence diagram","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C84780729","wikidata":"https://www.wikidata.org/wiki/Q7837579","display_name":"Tree diagram","level":4,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.640","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.640","pdf_url":"https://aclanthology.org/2025.emnlp-main.640.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.640","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.640","pdf_url":"https://aclanthology.org/2025.emnlp-main.640.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036542.pdf","grobid_xml":"https://content.openalex.org/works/W4416036542.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diagrams":[0],"play":[1],"a":[2,40,95],"central":[3],"role":[4],"in":[5,49,59],"research":[6,151],"papers":[7],"for":[8,81],"conveying":[9],"ideas,":[10],"yet":[11],"they":[12],"are":[13,22],"often":[14],"notoriously":[15],"complex":[16],"and":[17,70,78,117,123,135],"labor-intensive":[18],"to":[19,31,44,65,100],"create.Although":[20],"diagrams":[21,34,47,87,103,109,144],"presented":[23],"as":[24,52,110,115,120],"images,":[25],"standard":[26],"image":[27],"generative":[28],"models":[29,62],"struggle":[30],"produce":[32],"clear":[33],"with":[35],"well-defined":[36],"structure.We":[37],"argue":[38],"that":[39],"promising":[41],"direction":[42],"is":[43],"generate":[45],"demonstration":[46,102],"directly":[48],"textual":[50],"form":[51],"SVGs,":[53],"which":[54],"can":[55],"leverage":[56],"recent":[57,150],"advances":[58],"large":[60],"language":[61],"(LLMs).However,":[63],"due":[64],"the":[66,71,83,138,155,163,174],"complexity":[67],"of":[68,74,85,131,157,166,176],"components":[69],"multimodal":[72],"nature":[73],"diagrams,":[75],"sufficiently":[76],"discriminative":[77],"explainable":[79],"metrics":[80,169],"evaluating":[82],"quality":[84,126],"LLM-generated":[86,177],"remain":[88],"lacking.In":[89],"this":[90],"paper,":[91],"we":[92,141,160],"propose":[93],"DiagramEval,":[94],"novel":[96],"evaluation":[97],"metric":[98],"designed":[99],"assess":[101],"generated":[104],"by":[105,146],"LLMs.Specifically,":[106],"DiagramEval":[107],"conceptualizes":[108],"graphs,":[111],"treating":[112],"text":[113],"elements":[114],"nodes":[116],"their":[118],"connections":[119],"directed":[121],"edges,":[122],"evaluates":[124],"diagram":[125],"using":[127],"two":[128],"new":[129],"groups":[130],"metrics:":[132],"node":[133],"alignment":[134],"path":[136],"alignment.For":[137],"first":[139],"time,":[140],"effectively":[142],"evaluate":[143],"produced":[145],"stateof-the-art":[147],"LLMs":[148],"on":[149],"literature,":[152],"quantitatively":[153],"demonstrating":[154],"validity":[156],"our":[158,167],"metrics.Furthermore,":[159],"show":[161],"how":[162],"enhanced":[164],"explainability":[165],"proposed":[168],"offers":[170],"valuable":[171],"insights":[172],"into":[173],"characteristics":[175],"diagrams.":[178]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-11-08T00:00:00"}