{"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/todo-enhancing-llm-alignment-with-ternary","title":"TODO: Enhancing LLM Alignment with Ternary Preferences","arxiv_id":"2411.02442","date":"2024-11-02","proceeding":null,"authors":["Yuxiang Guo","Lu Yin","Bo Jiang","JiaQi Zhang"],"abstract":"Aligning large language models (LLMs) with human intent is critical for enhancing their performance across a variety of tasks. Standard alignment techniques, such as Direct Preference Optimization (DPO), often rely on the binary Bradley-Terry (BT) model, which can struggle to capture the complexities of human preferences -- particularly in the presence of noisy or inconsistent labels and frequent ties. To address these limitations, we introduce the Tie-rank Oriented Bradley-Terry model (TOBT), an extension of the BT model that explicitly incorporates ties, enabling more nuanced preference representation. Building on this, we propose Tie-rank Oriented Direct Preference Optimization (TODO), a novel alignment algorithm that leverages TOBT's ternary ranking system to improve preference alignment. In evaluations on Mistral-7B and Llama 3-8B models, TODO consistently outperforms DPO in modeling preferences across both in-distribution and out-of-distribution datasets. Additional assessments using MT Bench and benchmarks such as Piqa, ARC-c, and MMLU further demonstrate TODO's superior alignment performance. Notably, TODO also shows strong results in binary preference alignment, highlighting its versatility and potential for broader integration into LLM alignment. The implementation details can be found in https://github.com/XXares/TODO.","url_abs":"https://arxiv.org/abs/2411.02442v2","url_pdf":"https://arxiv.org/pdf/2411.02442v2.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":"todo-enhancing-llm-alignment-with-ternary","repo_url":"https://github.com/xxares/todo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"task_slug":"mmlu","task_name":"MMLU"}],"methods":[{"method_slug":"dpo","method_name":"DPO"},{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.02442","atlas_url":"https://app.syntology.ai/?focus=2411.02442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02442"}},"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":"deterministic:regex_extraction","url":"https://github.com/XXares/TODO","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xxares/todo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"6744441ca5bd1ea7","entry":"apply_chat_template","repo":"XXares/TODO","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/XXares/TODO/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6744441ca5bd1ea7"}},{"code_sha256_prefix":"f4b89d549bca2365","entry":"create_model","repo":"XXares/TODO","repo_kind":"official","path":"dpo_tie_train.py","file_url":"https://github.com/XXares/TODO/blob/HEAD/dpo_tie_train.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4b89d549bca2365"}},{"code_sha256_prefix":"8914ec0b7ae7a97f","entry":"create_tie_model","repo":"XXares/TODO","repo_kind":"official","path":"dpo_tie_eval.py","file_url":"https://github.com/XXares/TODO/blob/HEAD/dpo_tie_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8914ec0b7ae7a97f"}},{"code_sha256_prefix":"39e3cf1d3ab26978","entry":"pad_to_length","repo":"XXares/TODO","repo_kind":"official","path":"utils/dpo_tie_trainer_eval.py","file_url":"https://github.com/XXares/TODO/blob/HEAD/utils/dpo_tie_trainer_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39e3cf1d3ab26978"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}