{"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/improving-weak-to-strong-generalization-with-1","title":"Improving Weak-to-Strong Generalization with Reliability-Aware Alignment","arxiv_id":"2406.19032","date":"2024-06-27","proceeding":null,"authors":["Yue Guo","Yi Yang"],"abstract":"Large language models (LLMs) are now rapidly advancing and surpassing human abilities on many natural language tasks. However, aligning these super-human LLMs with human knowledge remains challenging because the supervision signals from human annotators may be wrong. This issue, known as the \"super-alignment\" problem, requires enhancing weak-to-strong generalization, where a strong LLM must generalize from imperfect supervision provided by a weaker source. To address this issue, we propose an approach to improve weak-to-strong generalization by involving the reliability of weak supervision signals in the alignment process. In our method, we query the weak supervisor for multiple answers, estimate the answer reliability, and enhance the alignment process by filtering out uncertain data or re-weighting reliable data. Experiments on four datasets demonstrate that our methods effectively identify the quality of weak labels and significantly enhance weak-to-strong generalization. Our work presents effective techniques for error-robust model alignment, reducing error propagation from noisy supervision and enhancing the accuracy and reliability of LLMs. Codes are publicly available at http://github.com/Irenehere/ReliableAlignment.","url_abs":"https://arxiv.org/abs/2406.19032v1","url_pdf":"https://arxiv.org/pdf/2406.19032v1.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":"improving-weak-to-strong-generalization-with-1","repo_url":"https://github.com/irenehere/reliablealignment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.19032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19032"}},"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/irenehere/reliablealignment","reach":null}],"summary":{"ran_honours":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"3a2bf35d401300c4","entry":"calculate_entropy","repo":"irenehere/reliablealignment","repo_kind":"official","path":"ETHICS/commonsense/our_method_uncertainty_filtering.py","file_url":"https://github.com/irenehere/reliablealignment/blob/HEAD/ETHICS/commonsense/our_method_uncertainty_filtering.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a2bf35d401300c4"}},{"code_sha256_prefix":"10bf4079d6dcab7a","entry":"prompt_model","repo":"irenehere/reliablealignment","repo_kind":"official","path":"ETHICS/commonsense/our_method_reweighting.py","file_url":"https://github.com/irenehere/reliablealignment/blob/HEAD/ETHICS/commonsense/our_method_reweighting.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"10bf4079d6dcab7a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}