{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/markedness-in-visual-semantic-ai","title":"Markedness in Visual Semantic AI","arxiv_id":"2205.11378","date":"2022-05-23","proceeding":null,"authors":["Robert Wolfe","Aylin Caliskan"],"abstract":"We evaluate the state-of-the-art multimodal \"visual semantic\" model CLIP (\"Contrastive Language Image Pretraining\") for biases related to the marking of age, gender, and race or ethnicity. Given the option to label an image as \"a photo of a person\" or to select a label denoting race or ethnicity, CLIP chooses the \"person\" label 47.9% of the time for White individuals, compared with 5.0% or less for individuals who are Black, East Asian, Southeast Asian, Indian, or Latino or Hispanic. The model is more likely to rank the unmarked \"person\" label higher than labels denoting gender for Male individuals (26.7% of the time) vs. Female individuals (15.2% of the time). Age affects whether an individual is marked by the model: Female individuals under the age of 20 are more likely than Male individuals to be marked with a gender label, but less likely to be marked with an age label, while Female individuals over the age of 40 are more likely to be marked based on age than Male individuals. We also examine the self-similarity (mean pairwise cosine similarity) for each social group, where higher self-similarity denotes greater attention directed by CLIP to the shared characteristics (age, race, or gender) of the social group. As age increases, the self-similarity of representations of Female individuals increases at a higher rate than for Male individuals, with the disparity most pronounced at the \"more than 70\" age range. All ten of the most self-similar social groups are individuals under the age of 10 or over the age of 70, and six of the ten are Female individuals. Existing biases of self-similarity and markedness between Male and Female gender groups are further exacerbated when the groups compared are individuals who are White and Male and individuals who are Black and Female. Results indicate that CLIP reflects the biases of the language and society which produced its training data.","url_abs":"https://arxiv.org/abs/2205.11378v1","url_pdf":"https://arxiv.org/pdf/2205.11378v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"markedness-in-visual-semantic-ai","repo_url":"https://github.com/wolferobert3/visual_semantic_markedness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.11378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11378"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wolferobert3/visual_semantic_markedness","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ff30348430b7bf9f","entry":"balance_on_characteristic","repo":"wolferobert3/visual_semantic_markedness","repo_kind":"official","path":"clip_functions.py","file_url":"https://github.com/wolferobert3/visual_semantic_markedness/blob/HEAD/clip_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff30348430b7bf9f"}},{"code_sha256_prefix":"7f52bcb4afbfbd67","entry":"get_image_features","repo":"wolferobert3/visual_semantic_markedness","repo_kind":"official","path":"clip_functions.py","file_url":"https://github.com/wolferobert3/visual_semantic_markedness/blob/HEAD/clip_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f52bcb4afbfbd67"}},{"code_sha256_prefix":"428a553e3f37cda6","entry":"get_text_features","repo":"wolferobert3/visual_semantic_markedness","repo_kind":"official","path":"clip_functions.py","file_url":"https://github.com/wolferobert3/visual_semantic_markedness/blob/HEAD/clip_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"428a553e3f37cda6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}