{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/beyond-one-preference-for-all-multi-objective","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","arxiv_id":"2310.03708","date":"2023-10-05","proceeding":null,"authors":["Zhanhui Zhou","Jie Liu","Jing Shao","Xiangyu Yue","Chao Yang","Wanli Ouyang","Yu Qiao"],"abstract":"A single language model, even when aligned with labelers through reinforcement learning from human feedback (RLHF), may not suit all human preferences. Recent approaches therefore prefer customization, gathering multi-dimensional feedback, and creating distinct reward models for each dimension. Different language models are then optimized for various preferences using multi-objective RLHF (MORLHF) with varying reward weights. However, RL fine-tuning is unstable and resource-heavy, especially with diverse and usually conflicting objectives. In this paper, we present Multi-Objective Direct Preference Optimization (MODPO), an RL-free extension of Direct Preference Optimization (DPO) for multiple alignment objectives. Essentially, MODPO folds language modeling directly into reward modeling, training language models as implicit collective reward models that combine all objectives with specific weights. MODPO theoretically yields the same optimal solutions as MORLHF but is practically more stable and efficient. Empirical results in safety alignment and long-form question answering show that MODPO matches or outperforms existing methods, producing a Pareto front of language models catering to diverse preferences with three times less computational resources compared to MORLHF. Code is available at https://github.com/ZHZisZZ/modpo.","url_abs":"https://arxiv.org/abs/2310.03708v4","url_pdf":"https://arxiv.org/pdf/2310.03708v4.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":"beyond-one-preference-for-all-multi-objective","repo_url":"https://github.com/ZHZisZZ/modpo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"beyond-one-preference-for-all-multi-objective","repo_url":"https://github.com/srzer/mod","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"long-form-question-answering","task_name":"Long Form Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"safety-alignment","task_name":"Safety Alignment"}],"methods":[{"method_slug":"opt","method_name":"OPT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.03708","atlas_url":"https://app.syntology.ai/?focus=2310.03708","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2310.03708"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2310.03708\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2310.03708"},"call":"get_concepts_for_paper(arxiv_id=\"2310.03708\")"}],"by_repo":[{"repo":"ZHZisZZ/modpo","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2403.19159"],"harvested_for_calls":[{"arxiv_id":"2403.19159","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.19159"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.19159\")"}]},{"repo":"srzer/mod","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["2402.10207","2406.18853","2410.04070"],"harvested_for_calls":[{"arxiv_id":"2402.10207","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.10207"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.10207\")"},{"arxiv_id":"2406.18853","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2406.18853"},"call":"get_harvested_code_for_paper(arxiv_id=\"2406.18853\")"},{"arxiv_id":"2410.04070","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.04070"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.04070\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2059dd22cae7b2c3228700a78f853656d12a8bc0cf48799dc310df968c0fb0c7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}