{"id":"https://openalex.org/W4416036068","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.90","title":"Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability","display_name":"Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036068","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.90"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.90","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.90","pdf_url":"https://aclanthology.org/2025.findings-emnlp.90.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.90.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dong Shu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Shu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738978","display_name":"Haiyan Zhao","orcid":"https://orcid.org/0000-0003-3544-9855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiyan Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006349984","display_name":"Jingyu Hu","orcid":"https://orcid.org/0000-0002-2975-5808"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyu Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002349071","display_name":"Weiru Liu","orcid":"https://orcid.org/0000-0001-8356-1361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiru Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076250758","display_name":"Ali Payani","orcid":"https://orcid.org/0000-0003-4054-2958"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Payani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007660467","display_name":"Cheng L\u00fc","orcid":"https://orcid.org/0000-0003-1746-7697"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072191151","display_name":"Mengnan Du","orcid":"https://orcid.org/0000-0002-1614-6069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengnan Du","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":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1713","last_page":"1735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9225000143051147,"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":0.9225000143051147,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.025499999523162842,"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":0.006800000090152025,"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/inference","display_name":"Inference","score":0.5519999861717224},{"id":"https://openalex.org/keywords/lens","display_name":"Lens (geology)","score":0.5303999781608582},{"id":"https://openalex.org/keywords/through-the-lens-metering","display_name":"Through-the-lens metering","score":0.47200000286102295},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3296000063419342},{"id":"https://openalex.org/keywords/experimental-data","display_name":"Experimental data","score":0.2637999951839447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6043000221252441},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C43091099","wikidata":"https://www.wikidata.org/wiki/Q1067788","display_name":"Through-the-lens metering","level":3,"score":0.47200000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44200000166893005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.2522999942302704},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.90","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.90","pdf_url":"https://aclanthology.org/2025.findings-emnlp.90.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:oai:research-information.bris.ac.uk:openaire/81090681-454e-4cd3-8d53-f783fc94091f","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/81090681-454e-4cd3-8d53-f783fc94091f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"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":"Shu, D, Zhao, H, Hu, J, Liu, W, Payani, A, Cheng, L & Du, M 2025, Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability. in C Christodoulopoulos, T Chakraborty, C Rose & V Peng (eds), Findings of the Association for Computational Linguistics: EMNLP 2025. Association for Computational Linguistics, pp. 1713-1735. https://doi.org/10.18653/v1/2025.findings-emnlp.90","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.90","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.90","pdf_url":"https://aclanthology.org/2025.findings-emnlp.90.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/G2617680309","display_name":null,"funder_award_id":"R01AG091762","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5642320712","display_name":"Collaborative Research: III:  Medium: Knowledge discovery from highly heterogeneous, sparse and private data in biomedical informatics","funder_award_id":"2312862","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8964793212","display_name":"CAREER: Conformal Methods for Responsible Language Models","funder_award_id":"2440542","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G9760920","display_name":"Collaborative Research: III: Medium: Towards Effective Detection and Mitigation for Shortcut Learning: A Data Modeling Framework","funder_award_id":"2310261","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036068.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"in":[8,39],"processing":[9],"both":[10],"visual":[11,22],"and":[12,23,37,55,60,74,110,127],"textual":[13,24],"information.":[14],"However,":[15],"the":[16,48,88,91,121],"critical":[17],"challenge":[18],"of":[19,35,50,102],"alignment":[20,36],"between":[21],"representations":[25],"is<br/>not":[26],"fully":[27],"understood.":[28],"This":[29],"survey":[30],"presents":[31],"a":[32,99],"comprehensive":[33,100],"examination":[34],"misalignment":[38,66,81],"LVLMs":[40],"through":[41],"an":[42],"explainability":[43,129],"lens.":[44],"We":[45,63,97],"first":[46],"examine":[47],"fundamentals":[49],"alignment,":[51],"exploring":[52],"its":[53],"representational":[54],"behavioral":[56],"aspects,":[57],"training":[58],"methodologies,":[59],"theoretical":[61],"foundations.":[62],"then":[64],"analyze":[65],"phenomena":[67],"across":[68],"three":[69],"semantic":[70],"levels:":[71,87],"object,":[72],"attribute,":[73],"relational":[75],"misalignment.":[76],"Our":[77],"investigation":[78],"reveals":[79],"that":[80],"emerges":[82],"from":[83],"challenges":[84],"at":[85],"multiple":[86],"data":[89],"level,":[90,93],"model":[92],"and<br/>the":[94],"inference":[95],"level.":[96],"provide":[98],"review":[101],"existing":[103],"mitigation":[104],"strategies,":[105],"categorizing":[106],"them":[107],"into":[108],"parameter-frozen":[109],"parameter-tuning":[111],"approaches.":[112],"Finally,":[113],"we":[114],"outline":[115],"promising":[116],"future":[117],"research":[118],"directions,":[119],"emphasizing":[120],"need":[122],"for":[123],"standardized":[124],"evaluation":[125],"protocols":[126],"in-depth":[128],"studies.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}