{"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/weak-to-strong-extrapolation-expedites","title":"Weak-to-Strong Extrapolation Expedites Alignment","arxiv_id":"2404.16792","date":"2024-04-25","proceeding":null,"authors":["Chujie Zheng","Ziqi Wang","Heng Ji","Minlie Huang","Nanyun Peng"],"abstract":"The open-source community is experiencing a surge in the release of large language models (LLMs) that are trained to follow instructions and align with human preference. However, further training to improve them still requires expensive computational resources and data annotations. Is it possible to bypass additional training and cost-effectively acquire better-aligned models? Inspired by the literature on model interpolation, we propose a simple method called ExPO to boost LLMs' alignment with human preference. Utilizing a model that has undergone alignment training (e.g., via DPO or RLHF) and its initial SFT checkpoint, ExPO directly obtains a better-aligned model by extrapolating from the weights of the initial and the aligned models, which implicitly optimizes the alignment objective via first-order approximation. Through experiments with twelve open-source LLMs on HuggingFace, we demonstrate that ExPO consistently improves off-the-shelf DPO/RLHF models, as evaluated on the mainstream LLM benchmarks AlpacaEval 2.0 and MT-Bench. Moreover, ExPO exhibits remarkable scalability across various model sizes (from 1.8B to 70B) and capabilities. Through controlled experiments and further empirical analyses, we shed light on the essence of ExPO amplifying the reward signal learned during alignment training. Our work demonstrates the efficacy of model extrapolation in expediting the alignment of LLMs with human preference, suggesting a promising direction for future research.","url_abs":"https://arxiv.org/abs/2404.16792v2","url_pdf":"https://arxiv.org/pdf/2404.16792v2.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":"weak-to-strong-extrapolation-expedites","repo_url":"https://github.com/chujiezheng/llm-extrapolation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"dpo","method_name":"DPO"},{"method_slug":"sft","method_name":"SFT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.16792","atlas_url":"https://app.syntology.ai/?focus=2404.16792","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":"2404.16792"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2404.16792\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2404.16792"},"call":"get_concepts_for_paper(arxiv_id=\"2404.16792\")"}],"by_repo":[{"repo":"chujiezheng/llm-extrapolation","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"232db12970f6777747f1f24653b807d67fbd0a82f55eb58075cb31f8271a6676","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}