{"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/on-the-safety-of-conversational-models","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","arxiv_id":"2110.08466","date":"2021-10-16","proceeding":"Findings (ACL) 2022 5","authors":["Hao Sun","Guangxuan Xu","Jiawen Deng","Jiale Cheng","Chujie Zheng","Hao Zhou","Nanyun Peng","Xiaoyan Zhu","Minlie Huang"],"abstract":"Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety problems remain under-defined and the corresponding dataset is scarce. We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works. To spur research in this direction, we compile DiaSafety, a dataset with rich context-sensitive unsafe examples. Experiments show that existing safety guarding tools fail severely on our dataset. As a remedy, we train a dialogue safety classifier to provide a strong baseline for context-sensitive dialogue unsafety detection. With our classifier, we perform safety evaluations on popular conversational models and show that existing dialogue systems still exhibit concerning context-sensitive safety problems.","url_abs":"https://arxiv.org/abs/2110.08466v2","url_pdf":"https://arxiv.org/pdf/2110.08466v2.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":"on-the-safety-of-conversational-models","repo_url":"https://github.com/thu-coai/diasafety","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.08466","atlas_url":"https://app.syntology.ai/?focus=2110.08466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08466"}},"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/thu-coai/diasafety","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"3349be060ae9fe89","entry":"get_loader","repo":"thu-coai/diasafety","repo_kind":"official","path":"codes/mix_train.py","file_url":"https://github.com/thu-coai/diasafety/blob/HEAD/codes/mix_train.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3349be060ae9fe89"}},{"code_sha256_prefix":"0862498ca3211ec4","entry":"get_loader_resp","repo":"thu-coai/diasafety","repo_kind":"official","path":"codes/mix_train.py","file_url":"https://github.com/thu-coai/diasafety/blob/HEAD/codes/mix_train.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0862498ca3211ec4"}},{"code_sha256_prefix":"c2357b08a012370c","entry":"evaluate","repo":"thu-coai/diasafety","repo_kind":"official","path":"codes/mix_train.py","file_url":"https://github.com/thu-coai/diasafety/blob/HEAD/codes/mix_train.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2357b08a012370c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}