Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models Article Swipe
Jiaqi Li
,
Chuanyi Zhang
,
Miaozeng Du
,
Hui Zhang
,
Yongrui Chen
,
Qianshan Wei
,
Junfeng Fang
,
Ruipeng Wang
,
Shmushkovich Bi
,
Guilin Qi
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2025.findings-acl.630
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2025.findings-acl.630
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.18653/v1/2025.findings-acl.630
- https://aclanthology.org/2025.findings-acl.630.pdf
- OA Status
- gold
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4412888316
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4412888316Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.18653/v1/2025.findings-acl.630Digital Object Identifier
- Title
-
Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative ModelsWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-01-01Full publication date if available
- Authors
-
Jiaqi Li, Chuanyi Zhang, Miaozeng Du, Hui Zhang, Yongrui Chen, Qianshan Wei, Junfeng Fang, Ruipeng Wang, Shmushkovich Bi, Guilin QiList of authors in order
- Landing page
-
https://doi.org/10.18653/v1/2025.findings-acl.630Publisher landing page
- PDF URL
-
https://aclanthology.org/2025.findings-acl.630.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://aclanthology.org/2025.findings-acl.630.pdfDirect OA link when available
- Concepts
-
Generative grammar, Security token, Computer science, Cognitive science, Artificial intelligence, Pixel, Human–computer interaction, Psychology, Computer securityTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4412888316 |
|---|---|
| doi | https://doi.org/10.18653/v1/2025.findings-acl.630 |
| ids.doi | https://doi.org/10.18653/v1/2025.findings-acl.630 |
| ids.openalex | https://openalex.org/W4412888316 |
| fwci | 0.0 |
| type | article |
| title | Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 12200 |
| biblio.first_page | 12179 |
| topics[0].id | https://openalex.org/T12031 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9397000074386597 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Speech and dialogue systems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C39890363 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8085941076278687 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q36108 |
| concepts[0].display_name | Generative grammar |
| concepts[1].id | https://openalex.org/C48145219 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7627631425857544 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1335365 |
| concepts[1].display_name | Security token |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.640261173248291 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C188147891 |
| concepts[3].level | 1 |
| concepts[3].score | 0.4647025465965271 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q147638 |
| concepts[3].display_name | Cognitive science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4472914934158325 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C160633673 |
| concepts[5].level | 2 |
| concepts[5].score | 0.42514437437057495 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q355198 |
| concepts[5].display_name | Pixel |
| concepts[6].id | https://openalex.org/C107457646 |
| concepts[6].level | 1 |
| concepts[6].score | 0.34661364555358887 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q207434 |
| concepts[6].display_name | Human–computer interaction |
| concepts[7].id | https://openalex.org/C15744967 |
| concepts[7].level | 0 |
| concepts[7].score | 0.26468586921691895 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[7].display_name | Psychology |
| concepts[8].id | https://openalex.org/C38652104 |
| concepts[8].level | 1 |
| concepts[8].score | 0.08779889345169067 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[8].display_name | Computer security |
| keywords[0].id | https://openalex.org/keywords/generative-grammar |
| keywords[0].score | 0.8085941076278687 |
| keywords[0].display_name | Generative grammar |
| keywords[1].id | https://openalex.org/keywords/security-token |
| keywords[1].score | 0.7627631425857544 |
| keywords[1].display_name | Security token |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.640261173248291 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/cognitive-science |
| keywords[3].score | 0.4647025465965271 |
| keywords[3].display_name | Cognitive science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.4472914934158325 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/pixel |
| keywords[5].score | 0.42514437437057495 |
| keywords[5].display_name | Pixel |
| keywords[6].id | https://openalex.org/keywords/human–computer-interaction |
| keywords[6].score | 0.34661364555358887 |
| keywords[6].display_name | Human–computer interaction |
| keywords[7].id | https://openalex.org/keywords/psychology |
| keywords[7].score | 0.26468586921691895 |
| keywords[7].display_name | Psychology |
| keywords[8].id | https://openalex.org/keywords/computer-security |
| keywords[8].score | 0.08779889345169067 |
| keywords[8].display_name | Computer security |
| language | en |
| locations[0].id | doi:10.18653/v1/2025.findings-acl.630 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://aclanthology.org/2025.findings-acl.630.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Findings of the Association for Computational Linguistics: ACL 2025 |
| locations[0].landing_page_url | https://doi.org/10.18653/v1/2025.findings-acl.630 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5100325946 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-3716-2543 |
| authorships[0].author.display_name | Jiaqi Li |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Jiaqi Li |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101465467 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8724-5796 |
| authorships[1].author.display_name | Chuanyi Zhang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chuanyi Zhang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100585277 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Miaozeng Du |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Miaozeng Du |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100685813 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-5047-025X |
| authorships[3].author.display_name | Hui Zhang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Hui Zhang |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5103157273 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-8934-3920 |
| authorships[4].author.display_name | Yongrui Chen |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Yongrui Chen |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5109722936 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Qianshan Wei |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Qianshan Wei |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5041233180 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-2094-8678 |
| authorships[6].author.display_name | Junfeng Fang |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Junfeng Fang |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5079140551 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-6569-9022 |
| authorships[7].author.display_name | Ruipeng Wang |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Ruipeng Wang |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5018174085 |
| authorships[8].author.orcid | https://orcid.org/0009-0004-1755-2749 |
| authorships[8].author.display_name | Shmushkovich Bi |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Sheng Bi |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5034606659 |
| authorships[9].author.orcid | https://orcid.org/0000-0003-0150-7236 |
| authorships[9].author.display_name | Guilin Qi |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Guilin Qi |
| authorships[9].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://aclanthology.org/2025.findings-acl.630.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T12031 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9397000074386597 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Speech and dialogue systems |
| related_works | https://openalex.org/W4388335561, https://openalex.org/W2970530566, https://openalex.org/W4288261899, https://openalex.org/W4307309205, https://openalex.org/W2967478618, https://openalex.org/W4385009901, https://openalex.org/W4385572700, https://openalex.org/W2997152889, https://openalex.org/W2380075625, https://openalex.org/W4285141722 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.18653/v1/2025.findings-acl.630 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://aclanthology.org/2025.findings-acl.630.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Findings of the Association for Computational Linguistics: ACL 2025 |
| best_oa_location.landing_page_url | https://doi.org/10.18653/v1/2025.findings-acl.630 |
| primary_location.id | doi:10.18653/v1/2025.findings-acl.630 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://aclanthology.org/2025.findings-acl.630.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Findings of the Association for Computational Linguistics: ACL 2025 |
| primary_location.landing_page_url | https://doi.org/10.18653/v1/2025.findings-acl.630 |
| publication_date | 2025-01-01 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index | |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 10 |
| citation_normalized_percentile.value | 0.14281635 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |