{"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/versusdebias-universal-zero-shot-debiasing","title":"VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary","arxiv_id":"2407.19524","date":"2024-07-28","proceeding":null,"authors":["Hanjun Luo","Ziye Deng","Haoyu Huang","Xuecheng Liu","Ruizhe Chen","Zuozhu Liu"],"abstract":"With the rapid development of Text-to-Image (T2I) models, biases in human image generation against demographic social groups become a significant concern, impacting fairness and ethical standards in AI. Some researchers propose their methods to tackle with the issue. However, existing methods are designed for specific models with fixed prompts, limiting their adaptability to the fast-evolving models and diverse practical scenarios. Moreover, they neglect the impact of hallucinations, leading to discrepancies between expected and actual results. To address these issues, we introduce VersusDebias, a novel and universal debiasing framework for biases in arbitrary T2I models, consisting of an array generation (AG) module and an image generation (IG) module. The self-adaptive AG module generates specialized attribute arrays to post-process hallucinations and debias multiple attributes simultaneously. The IG module employs a small language model to modify prompts according to the arrays and drives the T2I model to generate debiased images, enabling zero-shot debiasing. Extensive experiments demonstrate VersusDebias's capability to debias any models across gender, race, and age simultaneously. In both zero-shot and few-shot scenarios, VersusDebias outperforms existing methods, showcasing its exceptional utility. Our work is accessible at https://github.com/VersusDebias/VersusDebias to ensure reproducibility and facilitate further research.","url_abs":"https://arxiv.org/abs/2407.19524v3","url_pdf":"https://arxiv.org/pdf/2407.19524v3.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":"versusdebias-universal-zero-shot-debiasing","repo_url":"https://github.com/versusdebias/versusdebias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"small-language-model","task_name":"Small Language Model"}],"methods":[{"method_slug":"gam","method_name":"GAM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.19524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19524"}},"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/versusdebias/versusdebias","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"7fd6918321e1a8ca","entry":"find_overlap","repo":"versusdebias/versusdebias","repo_kind":"official","path":"dgm.py","file_url":"https://github.com/versusdebias/versusdebias/blob/HEAD/dgm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7fd6918321e1a8ca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}