{"id":"https://openalex.org/W4416034286","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.910","title":"Assessing the Sensitivity and Alignment of FOL Closeness Metrics","display_name":"Assessing the Sensitivity and Alignment of FOL Closeness Metrics","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034286","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.910"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.910","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.910","pdf_url":"https://aclanthology.org/2025.findings-emnlp.910.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.910.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067790912","display_name":"Ramya Thatikonda","orcid":"https://orcid.org/0009-0001-1192-778X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramya Keerthy Thatikonda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005792924","display_name":"Wray Buntine","orcid":"https://orcid.org/0000-0001-9292-1015"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wray Buntine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086032589","display_name":"Ehsan Shareghi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ehsan Shareghi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.35048338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16775","last_page":"16785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.04270000010728836,"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/T10467","display_name":"Psychometric Methodologies and Testing","score":0.04270000010728836,"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/T10730","display_name":"Language Development and Disorders","score":0.0210999995470047,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.016699999570846558,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.6503999829292297},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43790000677108765},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.429500013589859},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3188000023365021},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.29260000586509705},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2786000072956085}],"concepts":[{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.6503999829292297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5175999999046326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4717999994754791},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3368000090122223},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32710000872612},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3188000023365021},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.910","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.910","pdf_url":"https://aclanthology.org/2025.findings-emnlp.910.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.910","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.910","pdf_url":"https://aclanthology.org/2025.findings-emnlp.910.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034286.pdf","grobid_xml":"https://content.openalex.org/works/W4416034286.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"recent":[1],"successful":[2],"paradigm":[3],"of":[4,17,32,46,67,93,174],"solving":[5],"logical":[6],"reasoning":[7],"problems":[8],"with":[9],"tool-augmented":[10],"large":[11],"language":[12,19],"models":[13],"(LLMs)":[14],"leverages":[15],"translation":[16],"natural":[18],"(NL)":[20],"statements":[21,113],"into":[22],"First-Order":[23],"Logic":[24],"(FOL)":[25],"and":[26,37,54,71,81,96,107,154,168,185],"external":[27],"theorem":[28],"provers.However,":[29],"the":[30,44,65,87,124,136,146,155,172],"correctness":[31],"FOL":[33,80,94,112,156],"statements,":[34],"comprising":[35],"operators":[36],"text,":[38],"often":[39],"go":[40],"unverified":[41],"due":[42],"to":[43,74,110,114,188],"lack":[45],"a":[47,61,78,90,97,132,163],"reliable":[48],"evaluation":[49],"metric":[50,116,120,138,149,157],"for":[51,140,151,158],"comparing":[52,123],"generated":[53],"ground-truth":[55,111],"FOLs.In":[56],"this":[57],"paper,":[58],"we":[59,103,177],"conduct":[60],"comprehensive":[62],"study":[63],"on":[64],"sensitivity":[66,186],"existing":[68],"NL-,":[69],"FOL-,":[70],"graph-based":[72],"metrics":[73,125,181],"capture":[75],"differences":[76],"between":[77,89,166],"sampled":[79],"its":[82],"corresponding":[83],"ground-truth.We":[84],"then":[85,118],"measure":[86],"alignment":[88,165],"metric-based":[91],"ranking":[92],"outputs":[95],"strong":[98],"LLM":[99,169],"asa-judge.To":[100],"do":[101],"this,":[102],"first":[104],"apply":[105],"operator":[106,143,160],"text-based":[108],"perturbations":[109],"assess":[115],"sensitivity.We":[117],"evaluate":[119],"robustness":[121,184],"by":[122],"against":[126],"LLMs":[127],"judgment.Our":[128],"empirical":[129],"findings":[130],"highlight":[131],"clear":[133],"oversensitivity":[134],"in":[135],"n-gram":[137],"BLEU":[139],"text":[141],"perturbations.The":[142],"perturbation":[144],"affects":[145],"semantic":[147,175],"graph":[148],"Smatch++":[150],"structural":[152],"changes,":[153],"specific":[159],"changes.We":[161],"observe":[162],"closer":[164],"BertScore":[167],"judgement,":[170],"proving":[171],"importance":[173],"evaluation.Additionally,":[176],"show":[178],"that":[179],"combining":[180],"enhances":[182],"both":[183],"compared":[187],"using":[189],"individual":[190],"metrics.":[191],"1":[192]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}