{"id":"https://openalex.org/W7160447869","doi":"https://doi.org/10.1162/tacl.a.617","title":"<i>Beyond One-Size-Fits-All</i> : Inversion Learning for Highly Effective NLG Evaluation Prompts","display_name":"<i>Beyond One-Size-Fits-All</i> : Inversion Learning for Highly Effective NLG Evaluation Prompts","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160447869","doi":"https://doi.org/10.1162/tacl.a.617"},"language":"en","primary_location":{"id":"doi:10.1162/tacl.a.617","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.617","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1162/tacl.a.617","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100580797","display_name":"Hanhua Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hanhua Hong","raw_affiliation_strings":["The University of Manchester, UK. hanhua.hong@postgrad.manchester.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Manchester, UK. hanhua.hong@postgrad.manchester.ac.uk","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073544000","display_name":"Chenghao Xiao","orcid":"https://orcid.org/0000-0001-7623-8232"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chenghao Xiao","raw_affiliation_strings":["Durham University, UK. chenghao.xiao@durham.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University, UK. chenghao.xiao@durham.ac.uk","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134180971","display_name":"Yang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["The University of Manchester, UK. yang.yang.wang-27@postgrad.manchester.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Manchester, UK. yang.yang.wang-27@postgrad.manchester.ac.uk","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093980811","display_name":"Yiqi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yiqi Liu","raw_affiliation_strings":["The University of Manchester, UK. yiqi.liu@manchester.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Manchester, UK. yiqi.liu@manchester.ac.uk","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135519070","display_name":"Wenge Rong","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenge Rong","raw_affiliation_strings":["Beihang University, China. w.rong@buaa.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, China. w.rong@buaa.edu.cn","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135530249","display_name":"Chenghua Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chenghua Lin","raw_affiliation_strings":["The University of Manchester, UK. chenghua.lin@manchester.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Manchester, UK. chenghua.lin@manchester.ac.uk","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54745131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"689","last_page":"710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.45239999890327454,"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":0.45239999890327454,"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":0.241799995303154,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.057100001722574234,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/scalability","display_name":"Scalability","score":0.6575000286102295},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6147000193595886},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.5616999864578247},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4212999939918518},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3919999897480011},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.33649998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9114000201225281},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6575000286102295},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6147000193595886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593999981880188},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.5616999864578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4805999994277954},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4212999939918518},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1162/tacl.a.617","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.617","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1162/tacl.a.617","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.617","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2972664115","https://openalex.org/W3034188538","https://openalex.org/W3096738375","https://openalex.org/W3098267758","https://openalex.org/W3109862485","https://openalex.org/W3159259047","https://openalex.org/W4318819000","https://openalex.org/W4384616038","https://openalex.org/W4385572077","https://openalex.org/W4385572754","https://openalex.org/W4386554921","https://openalex.org/W4389518843","https://openalex.org/W4389519239","https://openalex.org/W4389519254","https://openalex.org/W4389520346","https://openalex.org/W4389520756","https://openalex.org/W4398771009","https://openalex.org/W4399116440","https://openalex.org/W4401798709","https://openalex.org/W4402667093","https://openalex.org/W4402670032","https://openalex.org/W4402671934","https://openalex.org/W4404782727","https://openalex.org/W4404782954","https://openalex.org/W4404792952","https://openalex.org/W4407719110","https://openalex.org/W4411113469","https://openalex.org/W4411119607","https://openalex.org/W4411120447","https://openalex.org/W4411120604","https://openalex.org/W4412944661","https://openalex.org/W4415797059","https://openalex.org/W4416035346","https://openalex.org/W7126428401"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Evaluating":[1],"natural":[2],"language":[3],"generation":[4,80],"systems":[5],"is":[6,18],"challenging":[7],"due":[8],"to":[9,44,52,73],"the":[10,19,78,97],"diversity":[11],"of":[12,27,81],"valid":[13],"outputs.":[14],"While":[15],"human":[16],"evaluation":[17,85,93],"gold":[20],"standard,":[21],"it":[22],"suffers":[23],"from":[24,69],"inconsistencies,":[25],"lack":[26],"standardization,":[28],"and":[29,95,108,120],"demographic":[30],"biases,":[31],"limiting":[32],"reproducibility.":[33],"LLM-based":[34,122],"evaluators":[35],"offer":[36],"a":[37,91,114],"scalable":[38],"alternative":[39],"but":[40],"are":[41],"highly":[42,82],"sensitive":[43],"prompt":[45,102],"design,":[46],"where":[47],"small":[48],"variations":[49],"can":[50],"lead":[51],"significant":[53],"discrepancies.":[54],"In":[55],"this":[56],"work,":[57],"we":[58],"propose":[59],"an":[60],"inversion":[61],"learning":[62],"method":[63,88],"that":[64],"learns":[65],"effective":[66],"reverse":[67],"mappings":[68],"model":[70],"outputs":[71],"back":[72],"their":[74],"input":[75],"instructions,":[76],"enabling":[77],"automatic":[79],"effective,":[83],"model-specific":[84],"prompts.":[86],"Our":[87,110],"requires":[89],"only":[90],"single":[92],"sample":[94],"eliminates":[96],"need":[98],"for":[99,117],"time-consuming":[100],"manual":[101],"engineering,":[103],"thereby":[104],"improving":[105],"both":[106],"efficiency":[107],"robustness.":[109],"work":[111],"contributes":[112],"toward":[113],"new":[115],"direction":[116],"more":[118],"robust":[119],"efficient":[121],"evaluation.":[123]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-05-07T00:00:00"}