{"id":"https://openalex.org/W4385573386","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.753","title":"On the Limitations of Reference-Free Evaluations of Generated Text","display_name":"On the Limitations of Reference-Free Evaluations of Generated Text","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385573386","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.753"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.emnlp-main.753","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.753","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.753","pdf_url":"https://aclanthology.org/2022.emnlp-main.753.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.emnlp-main.753.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007708364","display_name":"Daniel Deutsch","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Deutsch","raw_affiliation_strings":["Google Research University of Pennsylvania","Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089112142","display_name":"Rotem Dror","orcid":"https://orcid.org/0000-0002-9433-8410","observed_orcids":["https://orcid.org/0000-0002-9433-8410"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rotem Dror","raw_affiliation_strings":["Google Research University of Pennsylvania","University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023802054","display_name":"Dan Roth","orcid":"https://orcid.org/0009-0002-1447-5173","observed_orcids":["https://orcid.org/0009-0002-1447-5173"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Roth","raw_affiliation_strings":["Google Research University of Pennsylvania","University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5238,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.94865927,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10960","last_page":"10977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7627000212669373,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.7627000212669373,"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/T10028","display_name":"Topic Modeling","score":0.19509999454021454,"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/T13629","display_name":"Text Readability and Simplification","score":0.009100000374019146,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reference-free-evaluation","display_name":"reference-free evaluation","score":0.8709999918937683},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.47999998927116394},{"id":"https://openalex.org/keywords/text-summarization","display_name":"text summarization","score":0.7929999828338623},{"id":"https://openalex.org/keywords/metric-optimization","display_name":"metric optimization","score":0.43799999356269836},{"id":"https://openalex.org/keywords/human-written-text","display_name":"human-written text","score":0.4620000123977661},{"id":"https://openalex.org/keywords/model-behavior-analysis","display_name":"model behavior analysis","score":0.515999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8530393838882446},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.846102237701416},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.686863362789154},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5916458368301392},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5541144609451294},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5295599102973938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5141308903694153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5113393664360046},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4957643449306488},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42367294430732727},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3409905433654785},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2022.emnlp-main.753","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.753","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.753","pdf_url":"https://aclanthology.org/2022.emnlp-main.753.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.12563","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.12563","pdf_url":"https://arxiv.org/pdf/2210.12563","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.12563","doi":"https://doi.org/10.48550/arxiv.2210.12563","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.12563","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.emnlp-main.753","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.753","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.753","pdf_url":"https://aclanthology.org/2022.emnlp-main.753.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1472423617","display_name":null,"funder_award_id":"FA8750-19-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G638997368","display_name":null,"funder_award_id":"2019-19051600006","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320337349","display_name":"NIH Office of the Director","ror":"https://ror.org/00fj8a872"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385573386.pdf","grobid_xml":"https://content.openalex.org/works/W4385573386.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W23077562","https://openalex.org/W179314280","https://openalex.org/W2101105183","https://openalex.org/W2120481102","https://openalex.org/W2136657878","https://openalex.org/W2144933361","https://openalex.org/W2154652894","https://openalex.org/W2251023345","https://openalex.org/W2798362442","https://openalex.org/W2919023804","https://openalex.org/W2936695845","https://openalex.org/W2952138241","https://openalex.org/W2963341956","https://openalex.org/W2963929190","https://openalex.org/W2965373594","https://openalex.org/W2970295111","https://openalex.org/W2970791445","https://openalex.org/W2970886762","https://openalex.org/W2970892365","https://openalex.org/W2971120958","https://openalex.org/W2982399380","https://openalex.org/W3008926737","https://openalex.org/W3016254928","https://openalex.org/W3023366413","https://openalex.org/W3023783150","https://openalex.org/W3035628162","https://openalex.org/W3045321166","https://openalex.org/W3087597081","https://openalex.org/W3093429745","https://openalex.org/W3105678454","https://openalex.org/W3116868506","https://openalex.org/W3153469116","https://openalex.org/W3153947101","https://openalex.org/W3155708968","https://openalex.org/W3191640844","https://openalex.org/W3201081655","https://openalex.org/W3205309080","https://openalex.org/W3211758383","https://openalex.org/W3211912523","https://openalex.org/W4224280227","https://openalex.org/W4225302158","https://openalex.org/W4226269280","https://openalex.org/W4287889965"],"related_works":["https://openalex.org/W4406745597","https://openalex.org/W4224280227","https://openalex.org/W4226375873","https://openalex.org/W4402670032","https://openalex.org/W4385570969","https://openalex.org/W4392669905","https://openalex.org/W4404792887","https://openalex.org/W3101638716","https://openalex.org/W4285306212","https://openalex.org/W7125903298"],"abstract_inverted_index":{"There":[0],"is":[1,171],"significant":[2],"interest":[3],"in":[4,36,39,53,167],"developing":[5],"evaluation":[6],"metrics":[7,47,82,99,144],"which":[8,24,93,119,168],"accurately":[9],"estimate":[10],"the":[11,17,98,108,169],"quality":[12],"of":[13,19,158,160,176],"generated":[14,58],"text":[15],"without":[16],"aid":[18],"a":[20,165,177],"human-written":[21],"reference":[22],"text,":[23,59],"can":[25,100,129],"be":[26,67,101,130,146],"time":[27,105],"consuming":[28],"and":[29,51,60,126,153],"expensive":[30],"to":[31,56,69,85,90,106,123,172],"collect":[32],"or":[33,77],"entirely":[34],"unavailable":[35],"online":[37],"applications.However,":[38],"this":[40],"work,":[41],"we":[42,61,140],"demonstrate":[43],"that":[44,63,142],"these":[45],"reference-free":[46,81,143],"are":[48,83,114,120],"inherently":[49,115],"biased":[50,116,131],"limited":[52],"their":[54,124],"ability":[55],"evaluate":[57,91],"argue":[62],"they":[64,113,128],"should":[65,145],"not":[66],"used":[68,147],"measure":[70],"progress":[71],"on":[72],"tasks":[73],"like":[74],"machine":[75],"translation":[76],"summarization.We":[78],"show":[79],"how":[80,161],"equivalent":[84],"using":[86],"one":[87],"generation":[88],"model":[89,155],"another,":[92],"has":[94],"several":[95],"limitations:":[96],"(1)":[97],"optimized":[102],"at":[103],"test":[104],"find":[107],"approximate":[109],"best-possible":[110],"output,":[111],"(2)":[112],"toward":[117],"models":[118,163],"more":[121],"similar":[122],"own,":[125],"(3)":[127],"against":[132],"higher-quality":[133],"outputs,":[134],"including":[135],"those":[136],"written":[137],"by":[138],"humans.Therefore,":[139],"recommend":[141],"as":[148,174,179],"diagnostic":[149],"tools":[150],"for":[151],"analyzing":[152],"understanding":[154],"behavior":[156],"instead":[157],"measures":[159],"well":[162],"perform":[164],"task,":[166],"goal":[170],"achieve":[173],"high":[175],"score":[178],"possible.1":[180]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-08-05T00:00:00"}