{"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/aligners-decoupling-llms-and-alignment","title":"Aligners: Decoupling LLMs and Alignment","arxiv_id":"2403.04224","date":"2024-03-07","proceeding":null,"authors":["Lilian Ngweta","Mayank Agarwal","Subha Maity","Alex Gittens","Yuekai Sun","Mikhail Yurochkin"],"abstract":"Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be repeated for every LLM and alignment criterion. We propose to decouple LLMs and alignment by training aligner models that can be used to align any LLM for a given criteria on an as-needed basis, thus also reducing the potential negative impacts of alignment on performance. Our recipe for training the aligner models solely relies on synthetic data generated with a (prompted) LLM and can be easily adjusted for a variety of alignment criteria. We use the same synthetic data to train inspectors, binary miss-alignment classification models to guide a \"squad\" of multiple aligners. Our empirical results demonstrate consistent improvements when applying aligner squad to various LLMs, including chat-aligned models, across several instruction-following and red-teaming datasets.","url_abs":"https://arxiv.org/abs/2403.04224v4","url_pdf":"https://arxiv.org/pdf/2403.04224v4.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":"aligners-decoupling-llms-and-alignment","repo_url":"https://github.com/lilianngweta/aligners-and-inspectors","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"aligners-decoupling-llms-and-alignment","repo_url":"https://github.com/lilianngweta/aligners","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"red-teaming","task_name":"Red Teaming"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.04224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04224"}},"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/lilianngweta/aligners-and-inspectors","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lilianngweta/aligners","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"121d42fd1eb35b79","entry":"gather_responses","repo":"lilianngweta/aligners","repo_kind":"official","path":"generate-responses-for-eval/generate_using_individual_aligners.py","file_url":"https://github.com/lilianngweta/aligners/blob/HEAD/generate-responses-for-eval/generate_using_individual_aligners.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"121d42fd1eb35b79"}},{"code_sha256_prefix":"d4312699c6eef5c8","entry":"gather_responses","repo":"lilianngweta/aligners","repo_kind":"official","path":"generate-responses-for-eval/generate_responses_using_llms_baselines.py","file_url":"https://github.com/lilianngweta/aligners/blob/HEAD/generate-responses-for-eval/generate_responses_using_llms_baselines.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4312699c6eef5c8"}},{"code_sha256_prefix":"22ad67a68bb23eaa","entry":"prompt_formatter","repo":"lilianngweta/aligners","repo_kind":"official","path":"generate-responses-for-eval/generate_responses_using_llms_baselines.py","file_url":"https://github.com/lilianngweta/aligners/blob/HEAD/generate-responses-for-eval/generate_responses_using_llms_baselines.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22ad67a68bb23eaa"}},{"code_sha256_prefix":"574bb510af627949","entry":"prompt_formatter_with_output","repo":"lilianngweta/aligners","repo_kind":"official","path":"generate-responses-for-eval/generate_responses_using_llms_baselines.py","file_url":"https://github.com/lilianngweta/aligners/blob/HEAD/generate-responses-for-eval/generate_responses_using_llms_baselines.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"574bb510af627949"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}