{"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/alpacafarm-a-simulation-framework-for-methods-1","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","arxiv_id":"2305.14387","date":"2023-05-22","proceeding":"NeurIPS 2023 11","authors":["Yann Dubois","Xuechen Li","Rohan Taori","Tianyi Zhang","Ishaan Gulrajani","Jimmy Ba","Carlos Guestrin","Percy Liang","Tatsunori B. Hashimoto"],"abstract":"Large language models (LLMs) such as ChatGPT have seen widespread adoption due to their strong instruction-following abilities. Developing these LLMs involves a complex yet poorly understood workflow requiring training with human feedback. Replicating and understanding this instruction-following requires tackling three major challenges: the high cost of data collection, the lack of trustworthy evaluation, and the absence of reference method implementations. We address these challenges with AlpacaFarm, a simulator that enables research and development for learning from feedback at a low cost. First, we design LLM prompts to simulate human feedback that are 50x cheaper than crowdworkers and display high agreement with humans. Second, we propose an automatic evaluation and validate it against human instructions obtained on real-world interactions. Third, we contribute reference implementations for several methods (PPO, DPO, best-of-n, expert iteration, and more) that learn from pairwise feedback. Finally, as an end-to-end validation of AlpacaFarm, we train and evaluate eleven models on 10k pairs of real human feedback and show that rankings of models trained in AlpacaFarm match rankings of models trained on human data. As a demonstration of the research possible in AlpacaFarm, we find that methods that use a reward model can substantially improve over supervised fine-tuning and that our reference PPO implementation leads to a +10% improvement in win-rate against Davinci003. We release all components of AlpacaFarm at https://github.com/tatsu-lab/alpaca_farm.","url_abs":"https://arxiv.org/abs/2305.14387v4","url_pdf":"https://arxiv.org/pdf/2305.14387v4.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":"alpacafarm-a-simulation-framework-for-methods-1","repo_url":"https://github.com/tatsu-lab/alpaca_eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"alpacafarm-a-simulation-framework-for-methods-1","repo_url":"https://github.com/tatsu-lab/alpaca_farm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"}],"methods":[{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[{"slug":"alpacaeval","name":"AlpacaEval","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.14387","atlas_url":"https://app.syntology.ai/?focus=2305.14387","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":"2305.14387"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2305.14387\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2305.14387"},"call":"get_concepts_for_paper(arxiv_id=\"2305.14387\")"}],"by_repo":[{"repo":"tatsu-lab/alpaca_eval","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2606.10528"],"harvested_for_calls":[{"arxiv_id":"2606.10528","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2606.10528"},"call":"get_harvested_code_for_paper(arxiv_id=\"2606.10528\")"}]},{"repo":"tatsu-lab/alpaca_farm","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2501.09620"],"harvested_for_calls":[{"arxiv_id":"2501.09620","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2501.09620"},"call":"get_harvested_code_for_paper(arxiv_id=\"2501.09620\")"}]}],"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":"2b571770101cf12ecd39d84ef52770db5f388956e8188ba36e2b3855cec8cf86","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}