{"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/safesora-towards-safety-alignment-of","title":"SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset","arxiv_id":"2406.14477","date":"2024-06-20","proceeding":null,"authors":["Josef Dai","Tianle Chen","Xuyao Wang","Ziran Yang","Taiye Chen","Jiaming Ji","Yaodong Yang"],"abstract":"To mitigate the risk of harmful outputs from large vision models (LVMs), we introduce the SafeSora dataset to promote research on aligning text-to-video generation with human values. This dataset encompasses human preferences in text-to-video generation tasks along two primary dimensions: helpfulness and harmlessness. To capture in-depth human preferences and facilitate structured reasoning by crowdworkers, we subdivide helpfulness into 4 sub-dimensions and harmlessness into 12 sub-categories, serving as the basis for pilot annotations. The SafeSora dataset includes 14,711 unique prompts, 57,333 unique videos generated by 4 distinct LVMs, and 51,691 pairs of preference annotations labeled by humans. We further demonstrate the utility of the SafeSora dataset through several applications, including training the text-video moderation model and aligning LVMs with human preference by fine-tuning a prompt augmentation module or the diffusion model. These applications highlight its potential as the foundation for text-to-video alignment research, such as human preference modeling and the development and validation of alignment algorithms.","url_abs":"https://arxiv.org/abs/2406.14477v1","url_pdf":"https://arxiv.org/pdf/2406.14477v1.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":"safesora-towards-safety-alignment-of","repo_url":"https://github.com/pku-alignment/safe-sora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"safety-alignment","task_name":"Safety Alignment"},{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-alignment","task_name":"Video Alignment"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.14477","atlas_url":"https://app.syntology.ai/?focus=2406.14477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14477"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/pku-alignment/safe-sora","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"aae2ddd4c766507a","entry":"build_image_tower","repo":"pku-alignment/safe-sora","repo_kind":"official","path":"safe_sora/models/multimodal_encoder/builder.py","file_url":"https://github.com/pku-alignment/safe-sora/blob/HEAD/safe_sora/models/multimodal_encoder/builder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aae2ddd4c766507a"}},{"code_sha256_prefix":"6d6b281af73773f5","entry":"build_video_tower","repo":"pku-alignment/safe-sora","repo_kind":"official","path":"safe_sora/models/multimodal_encoder/builder.py","file_url":"https://github.com/pku-alignment/safe-sora/blob/HEAD/safe_sora/models/multimodal_encoder/builder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d6b281af73773f5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}