{"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/goodtriever-adaptive-toxicity-mitigation-with","title":"Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models","arxiv_id":"2310.07589","date":"2023-10-11","proceeding":null,"authors":["Luiza Pozzobon","Beyza Ermis","Patrick Lewis","Sara Hooker"],"abstract":"Considerable effort has been dedicated to mitigating toxicity, but existing methods often require drastic modifications to model parameters or the use of computationally intensive auxiliary models. Furthermore, previous approaches have often neglected the crucial factor of language's evolving nature over time. In this work, we present a comprehensive perspective on toxicity mitigation that takes into account its changing nature. We introduce Goodtriever, a flexible methodology that matches the current state-of-the-art toxicity mitigation while achieving 43% relative latency reduction during inference and being more computationally efficient. By incorporating a retrieval-based approach at decoding time, Goodtriever enables toxicity-controlled text generation. Our research advocates for an increased focus on adaptable mitigation techniques, which better reflect the data drift models face when deployed in the wild. Code and data are available at https://github.com/for-ai/goodtriever.","url_abs":"https://arxiv.org/abs/2310.07589v1","url_pdf":"https://arxiv.org/pdf/2310.07589v1.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":"goodtriever-adaptive-toxicity-mitigation-with","repo_url":"https://github.com/for-ai/goodtriever","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.07589","atlas_url":"https://app.syntology.ai/?focus=2310.07589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07589"}},"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/for-ai/goodtriever","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"ff535bf88cf43cfe","entry":"load_cache","repo":"for-ai/goodtriever","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/for-ai/goodtriever/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff535bf88cf43cfe"}},{"code_sha256_prefix":"c84f42372ddb0ae8","entry":"setup_tokenizer","repo":"for-ai/goodtriever","repo_kind":"official","path":"generation/models.py","file_url":"https://github.com/for-ai/goodtriever/blob/HEAD/generation/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c84f42372ddb0ae8"}},{"code_sha256_prefix":"5da8c7904857edeb","entry":"structure_output_filepath","repo":"for-ai/goodtriever","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/for-ai/goodtriever/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5da8c7904857edeb"}},{"code_sha256_prefix":"79236a47198404a3","entry":"unpack_scores","repo":"for-ai/goodtriever","repo_kind":"official","path":"utils/perspective_api.py","file_url":"https://github.com/for-ai/goodtriever/blob/HEAD/utils/perspective_api.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"79236a47198404a3"}},{"code_sha256_prefix":"6876cba1d1718afb","entry":"generate","repo":"for-ai/goodtriever","repo_kind":"official","path":"generation/base.py","file_url":"https://github.com/for-ai/goodtriever/blob/HEAD/generation/base.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":"6876cba1d1718afb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}