{"id":"https://openalex.org/W7123335113","doi":"https://doi.org/10.1109/esem64174.2025.00039","title":"Robust or Overfitted? Investigating the Generalization of Pretrained Models in Requirement Classification","display_name":"Robust or Overfitted? Investigating the Generalization of Pretrained Models in Requirement Classification","publication_year":2025,"publication_date":"2025-10-02","ids":{"openalex":"https://openalex.org/W7123335113","doi":"https://doi.org/10.1109/esem64174.2025.00039"},"language":"en","primary_location":{"id":"doi:10.1109/esem64174.2025.00039","doi":"https://doi.org/10.1109/esem64174.2025.00039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/esem64174.2025.00039","pdf_url":null,"source":{"id":"https://openalex.org/S4210197744","display_name":"Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement","issn_l":"1938-6451","issn":["1938-6451","1949-3770","1949-3789"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122892264","display_name":"Farha Kamal","orcid":"https://orcid.org/0009-0008-9659-737X","observed_orcids":["https://orcid.org/0009-0008-9659-737X"]},"institutions":[{"id":"https://openalex.org/I177898655","display_name":"Lamar University","ror":"https://ror.org/008ms5s18","country_code":"US","type":"education","lineage":["https://openalex.org/I177898655"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farha Kamal","raw_affiliation_strings":["Lamar University,Department of Computer Science,Beaumont,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lamar University,Department of Computer Science,Beaumont,TX,USA","institution_ids":["https://openalex.org/I177898655"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101486322","display_name":"Md Rakibul Islam","orcid":"https://orcid.org/0009-0009-9104-874X","observed_orcids":["https://orcid.org/0009-0009-9104-874X"]},"institutions":[{"id":"https://openalex.org/I177898655","display_name":"Lamar University","ror":"https://ror.org/008ms5s18","country_code":"US","type":"education","lineage":["https://openalex.org/I177898655"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Rakibul Islam","raw_affiliation_strings":["Lamar University,Department of Computer Science,Beaumont,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lamar University,Department of Computer Science,Beaumont,TX,USA","institution_ids":["https://openalex.org/I177898655"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177898655"],"apc_list":null,"apc_paid":null,"fwci":2.6576,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90959458,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"414","last_page":"420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10430","display_name":"Software Engineering Techniques and Practices","score":0.5249000191688538,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.5249000191688538,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.4253000020980835,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.020600000396370888,"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/non-functional-requirements","display_name":"non-functional requirements","score":0.8119999766349792},{"id":"https://openalex.org/keywords/requirements-classification","display_name":"requirements classification","score":0.9549999833106995},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8270000219345093},{"id":"https://openalex.org/keywords/cross-platform-transfer","display_name":"cross-platform transfer","score":0.8059999942779541},{"id":"https://openalex.org/keywords/cross-dataset-generalization","display_name":"cross-dataset generalization","score":0.7739999890327454},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.6909999847412109},{"id":"https://openalex.org/keywords/zero-shot-learning","display_name":"zero-shot learning","score":0.9940000176429749},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.8450000286102295},{"id":"https://openalex.org/keywords/prompt-based-classification","display_name":"prompt-based classification","score":0.6359999775886536},{"id":"https://openalex.org/keywords/domain-specific-fine-tuning","display_name":"domain-specific fine-tuning","score":0.7599999904632568},{"id":"https://openalex.org/keywords/sentence-embeddings","display_name":"sentence embeddings","score":0.8489999771118164},{"id":"https://openalex.org/keywords/informal-requirements","display_name":"informal requirements","score":0.46299999952316284},{"id":"https://openalex.org/keywords/promise-dataset","display_name":"PROMISE dataset","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8148000240325928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530999779701233},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.73089998960495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5803999900817871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5242000222206116},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C201305675","wikidata":"https://www.wikidata.org/wiki/Q852998","display_name":"Stakeholder","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C59488412","wikidata":"https://www.wikidata.org/wiki/Q187147","display_name":"Requirements analysis","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/esem64174.2025.00039","doi":"https://doi.org/10.1109/esem64174.2025.00039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/esem64174.2025.00039","pdf_url":null,"source":{"id":"https://openalex.org/S4210197744","display_name":"Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement","issn_l":"1938-6451","issn":["1938-6451","1949-3770","1949-3789"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1532113059","https://openalex.org/W1567427961","https://openalex.org/W2060736388","https://openalex.org/W2127626360","https://openalex.org/W2734338314","https://openalex.org/W2758004809","https://openalex.org/W2758253540","https://openalex.org/W2799028668","https://openalex.org/W2886486953","https://openalex.org/W2963341956","https://openalex.org/W2993303751","https://openalex.org/W3091973425","https://openalex.org/W4312278392","https://openalex.org/W4313563649","https://openalex.org/W4327919569","https://openalex.org/W4401357421","https://openalex.org/W4402759247"],"related_works":["https://openalex.org/W4414165984","https://openalex.org/W7131259885","https://openalex.org/W4414247303","https://openalex.org/W3091973425","https://openalex.org/W4411447701","https://openalex.org/W4313563649","https://openalex.org/W7220746831","https://openalex.org/W7133222239","https://openalex.org/W4416055025","https://openalex.org/W4385516995"],"abstract_inverted_index":{"Background:":[0],"Accurate":[1],"classification":[2,87],"of":[3,40,76],"nonfunctional":[4],"requirements":[5,41,47],"(NFRs)":[6],"is":[7,118],"essential":[8],"for":[9,85,199],"aligning":[10],"stakeholder":[11],"expectations":[12],"with":[13,130,167],"system":[14],"design":[15],"and":[16,26,79,94,106,114,122],"ensuring":[17],"software":[18],"quality.":[19],"While":[20],"transformer-based":[21],"models":[22,83,185],"such":[23],"as":[24],"PRCBERT":[25],"NORBERT":[27],"have":[28],"achieved":[29],"high":[30],"performance":[31,145,178],"in":[32,111,123,155,161,188],"supervised":[33,184],"settings,":[34],"their":[35],"generalizability":[36],"across":[37,88,149],"diverse":[38,200],"sources":[39],"remains":[42],"largely":[43],"unexplored.":[44],"In":[45,151,171],"practice,":[46],"originate":[48],"from":[49,53],"heterogeneous":[50],"platforms,":[51],"ranging":[52],"structured":[54],"specification":[55],"documents":[56],"to":[57,127],"informal":[58],"developer":[59],"discussions":[60],"on":[61],"forums":[62],"like":[63],"Stack":[64],"Overflow.":[65],"Aim:":[66],"This":[67],"study":[68],"provides":[69],"the":[70],"first":[71],"comprehensive,":[72],"bidirectional":[73],"cross-dataset":[74],"evaluation":[75],"domain-specific,":[77],"embedding-based,":[78],"promptbased":[80],"large":[81],"language":[82],"(LLMs)":[84],"NFR":[86,190],"two":[89],"contrasting":[90],"platforms:":[91],"PROMISE":[92],"(structured)":[93],"NFR-SO":[95],"(informal).":[96],"Method:":[97],"We":[98],"evaluate":[99],"domain-specific":[100],"finetuned":[101],"models,":[102,105,139],"sentence":[103],"embedding":[104],"prompt-based":[107],"LLMs":[108,193],"(including":[109],"GPT-4o)":[110],"both":[112,120],"zero-shot":[113,172],"few-shot":[115,156],"settings.":[116],"Performance":[117],"measured":[119],"in-domain":[121],"crossplatform":[124],"transfer":[125],"scenarios":[126],"assess":[128],"generalization":[129,166],"minimal":[131,168],"or":[132],"no":[133],"labeled":[134,169],"data.":[135,170],"Results:":[136],"Domain-specific":[137],"fine-tuned":[138],"although":[140],"effective":[141],"in-domain,":[142],"exhibit":[143],"substantial":[144],"degradation":[146],"when":[147],"transferred":[148],"platforms.":[150],"contrast,":[152],"LLMs-particularly":[153],"GPT-4o":[154,174],"mode-consistently":[157],"outperform":[158],"other":[159],"approaches":[160],"cross-platform":[162,189],"scenarios,":[163],"achieving":[164],"strong":[165],"mode,":[173],"also":[175],"demonstrates":[176],"robust":[177],"without":[179],"any":[180],"supervision.":[181],"Conclusions:":[182],"Traditional":[183],"face":[186],"limitations":[187],"classification.":[191],"Prompt-based":[192],"offer":[194],"a":[195],"scalable,":[196],"low-supervision":[197],"solution":[198],"requirement":[201],"sources.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-01-14T00:00:00"}