{"id":"https://openalex.org/W4416034820","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.673","title":"What if Othello-Playing Language Models Could See?","display_name":"What if Othello-Playing Language Models Could See?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034820","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.673"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.673","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.673","pdf_url":"https://aclanthology.org/2025.findings-emnlp.673.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.673.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100457118","display_name":"Xinyi Chen","orcid":"https://orcid.org/0000-0003-3321-2483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yifei Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifei Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055296248","display_name":"Jiaang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018609918","display_name":"Serge Belongie","orcid":"https://orcid.org/0000-0002-0388-5217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Serge Belongie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maarten de Rijke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018138946","display_name":"Anders S\u00f8gaard","orcid":"https://orcid.org/0000-0001-5250-4276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anders S\u00f8gaard","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30382142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12598","last_page":"12609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9575999975204468,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9575999975204468,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.011099999770522118,"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":0.003700000001117587,"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/robustness","display_name":"Robustness (evolution)","score":0.7081999778747559},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5956000089645386},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.5688999891281128},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.47429999709129333},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3849000036716461},{"id":"https://openalex.org/keywords/internal-model","display_name":"Internal model","score":0.37369999289512634},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.3483999967575073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7208999991416931},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7081999778747559},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5956000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5852000117301941},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41990000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4047999978065491},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.37369999289512634},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C175652121","wikidata":"https://www.wikidata.org/wiki/Q4379351","display_name":"Causal consistency","level":5,"score":0.2867000102996826},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.673","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.673","pdf_url":"https://aclanthology.org/2025.findings-emnlp.673.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"},{"id":"pmh:doi:10.3929/ethz-c-000795379","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/795379","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/9ed95052-2d0d-43b5-b7e2-0c890e9b2321","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/9ed95052-2d0d-43b5-b7e2-0c890e9b2321","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chen , X , Yuan , Y , Li , J , Belongie , S , de Rijke , M & S\u00f8gaard , A 2025 , What if Othello-Playing Language Models Could See? in Findings of the Association for Computational Linguistics: EMNLP 2025 . Association for Computational Linguistics (ACL) , pp. 12598-12609 , 2025 Conference on Empirical Methods in Natural Language Processing , Suzhou , China , 04/09/2025 . https://doi.org/10.18653/v1/2025.findings-emnlp.673","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.673","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.673","pdf_url":"https://aclanthology.org/2025.findings-emnlp.673.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":[{"id":"https://openalex.org/G1658026781","display_name":"Robust Generative Information Retrieval","funder_award_id":"101201510","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2124936668","display_name":"European Lighthouse of AI for Sustainability","funder_award_id":"101120237","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2289169492","display_name":"Fairness and Intersectional Non-Discrimination in Human Recommendation","funder_award_id":"101070212","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5550786340","display_name":"Hybrid Intelligence (HI): augmenting human intellect","funder_award_id":"024.004.022","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G6280615682","display_name":"Low Resource Chat-based Conversational Intelligence","funder_award_id":"NWA.1389.20.183","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G6640760388","display_name":"Trustworthy AI-based Systems for Sustainable Growth","funder_award_id":"KICH3.LTP.20.006","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320943","display_name":"Danmarks Grundforskningsfond","ror":"https://ror.org/00znyv691"},{"id":"https://openalex.org/F4320321008","display_name":"Universiteit van Amsterdam","ror":"https://ror.org/04dkp9463"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034820.pdf","grobid_xml":"https://content.openalex.org/works/W4416034820.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Language":[0],"models":[1],"are":[2],"often":[3],"said":[4],"to":[5,21],"face":[6],"a":[7,38,44,59],"symbol":[8],"grounding":[9],"problem.While":[10],"some":[11],"have":[12,25],"argued":[13],"the":[14,70,94],"problem":[15],"can":[16],"be":[17],"solved":[18],"without":[19],"resort":[20],"other":[22],"modalities,":[23],"many":[24],"speculated":[26],"that":[27,42,101],"grounded":[28],"learning":[29,79],"is":[30],"more":[31],"efficient.We":[32],"explore":[33],"this":[34],"question":[35],"in":[36],"Othello,":[37],"simplified,":[39],"rulebased":[40],"world":[41,51],"offers":[43],"controlled":[45],"and":[46,67,92,108],"interpretable":[47],"testbed":[48],"for":[49],"studying":[50],"understanding.Building":[52],"on":[53,64],"prior":[54],"work,":[55],"we":[56,75],"introduce":[57],"VIS-OTHELLO,":[58],"multi-modal":[60,78,102],"model":[61,120],"trained":[62],"jointly":[63],"move":[65],"sequences":[66],"board":[68],"images.Using":[69],"Othello":[71],"rule":[72],"understanding":[73],"task,":[74],"examine":[76],"whether":[77],"provides":[80],"advantages":[81],"over":[82],"text-only":[83],"approaches.We":[84],"further":[85],"evaluate":[86],"robustness":[87,109],"under":[88],"semantically":[89],"irrelevant":[90],"perturbations":[91],"analyze":[93],"consistency":[95],"of":[96],"cross-modal":[97],"alignment.Our":[98],"results":[99],"suggest":[100],"training":[103],"not":[104],"only":[105],"improves":[106],"performance":[107],"but":[110],"also":[111],"promotes":[112],"convergence":[113],"toward":[114],"shared":[115],"internal":[116],"representations":[117],"across":[118],"different":[119],"architectures.":[121]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-11-08T00:00:00"}