{"id":"https://openalex.org/W4417301034","doi":"https://doi.org/10.48550/arxiv.2505.12533","title":"Relation Extraction or Pattern Matching? Unravelling the Generalisation Limits of Language Models for Biographical RE","display_name":"Relation Extraction or Pattern Matching? Unravelling the Generalisation Limits of Language Models for Biographical RE","publication_year":2025,"publication_date":"2025-05-18","ids":{"openalex":"https://openalex.org/W4417301034","doi":"https://doi.org/10.48550/arxiv.2505.12533"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.12533","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12533","pdf_url":"https://arxiv.org/pdf/2505.12533","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.12533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114653423","display_name":"Varvara Arzt","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arzt, Varvara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020665735","display_name":"Allan Hanbury","orcid":"https://orcid.org/0000-0002-7149-5843","observed_orcids":["https://orcid.org/0000-0002-7149-5843"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanbury, Allan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060170090","display_name":"Michael Wiegand","orcid":"https://orcid.org/0000-0002-5403-1078","observed_orcids":["https://orcid.org/0000-0002-5403-1078"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wiegand, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029370035","display_name":"G\u00e1bor Recski","orcid":"https://orcid.org/0000-0001-5551-3100","observed_orcids":["https://orcid.org/0000-0001-5551-3100"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Recski, G\u00e1bor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088311840","display_name":"Terra Blevins","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Blevins, Terra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9872999787330627,"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":0.9872999787330627,"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":0.006599999964237213,"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":0.0010000000474974513,"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/relation-extraction","display_name":"relation extraction","score":0.9739999771118164},{"id":"https://openalex.org/keywords/cross-dataset-transfer","display_name":"cross-dataset transfer","score":0.7710000276565552},{"id":"https://openalex.org/keywords/spurious-correlations","display_name":"spurious correlations","score":0.8519999980926514},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.8880000114440918},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.8220000267028809},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8679999709129333},{"id":"https://openalex.org/keywords/few-shot-prompting","display_name":"few-shot prompting","score":0.9039999842643738},{"id":"https://openalex.org/keywords/zero-shot-learning","display_name":"zero-shot learning","score":0.9570000171661377}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8755999803543091},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7681999802589417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.675000011920929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6640999913215637},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6152999997138977},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49869999289512634},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.460999995470047},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45660001039505005},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42260000109672546},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.12533","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12533","pdf_url":"https://arxiv.org/pdf/2505.12533","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.2505.12533","doi":"https://doi.org/10.48550/arxiv.2505.12533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.12533","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.12533","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12533","pdf_url":"https://arxiv.org/pdf/2505.12533","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3092631491","https://openalex.org/W3133663111","https://openalex.org/W3037287267","https://openalex.org/W4385573472","https://openalex.org/W2952944718","https://openalex.org/W4285308265","https://openalex.org/W6979342190","https://openalex.org/W3087998754","https://openalex.org/W4396757532","https://openalex.org/W6979289584"],"abstract_inverted_index":{"Analysing":[0],"the":[1,72,80,88],"generalisation":[2],"capabilities":[3],"of":[4,74,82],"relation":[5],"extraction":[6],"(RE)":[7],"models":[8,30],"is":[9,66,99],"crucial":[10],"for":[11],"assessing":[12],"whether":[13],"they":[14],"learn":[15],"robust":[16,69],"relational":[17],"patterns":[18],"or":[19],"rely":[20],"on":[21,79],"spurious":[22],"correlations.":[23],"Our":[24,55],"cross-dataset":[25,90,115],"experiments":[26],"find":[27],"that":[28,59],"RE":[29,120],"struggle":[31],"with":[32,92,102],"unseen":[33],"data,":[34,94],"even":[35,106],"within":[36],"similar":[37],"domains.":[38],"Notably,":[39],"higher":[40],"intra-dataset":[41],"performance":[42,91],"does":[43],"not":[44],"indicate":[45],"better":[46],"transferability,":[47],"instead":[48],"often":[49],"signaling":[50],"overfitting":[51],"to":[52,68],"dataset-specific":[53],"artefacts.":[54],"results":[56],"also":[57],"show":[58],"data":[60,83],"quality,":[61],"rather":[62],"than":[63],"lexical":[64],"similarity,":[65],"key":[67],"transfer,":[70],"and":[71,128],"choice":[73],"optimal":[75],"adaptation":[76],"strategy":[77],"depends":[78],"quality":[81],"available:":[84],"while":[85],"fine-tuning":[86],"yields":[87],"best":[89],"high-quality":[93],"few-shot":[95],"in-context":[96],"learning":[97],"(ICL)":[98],"more":[100],"effective":[101],"noisier":[103],"data.":[104],"However,":[105],"in":[107,119],"these":[108],"cases,":[109],"zero-shot":[110],"baselines":[111],"occasionally":[112],"outperform":[113],"all":[114],"results.":[116],"Structural":[117],"issues":[118],"benchmarks,":[121],"such":[122],"as":[123],"single-relation":[124],"per":[125],"sample":[126],"constraints":[127],"non-standardised":[129],"negative":[130],"class":[131],"definitions,":[132],"further":[133],"hinder":[134],"model":[135],"transferability.":[136]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}