{"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/openassistant-conversations-democratizing-1","title":"OpenAssistant Conversations - Democratizing Large Language Model Alignment","arxiv_id":null,"date":"2023-09-26","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"Aligning large language models (LLMs) with human preferences has proven to drastically improve usability and has driven rapid adoption as demonstrated by ChatGPT.\nAlignment techniques such as supervised fine-tuning (\\textit{SFT}) and  reinforcement learning from human feedback (\\textit{RLHF}) greatly reduce the required skill and domain knowledge to effectively harness the capabilities of LLMs, increasing their accessibility and utility across various domains.\nHowever, state-of-the-art alignment techniques like \\textit{RLHF} rely on high-quality human feedback data, which is expensive to create and often remains proprietary.\nIn an effort to democratize research on large-scale alignment, we release OpenAssistant Conversations, a human-generated, human-annotated assistant-style conversation corpus consisting of 161,443 messages in 35 different languages, annotated with 461,292 quality ratings, resulting in over 10,000 complete and fully annotated conversation trees.\nThe corpus is a product of a worldwide crowd-sourcing effort involving over 13,500 volunteers.\nModels trained on OpenAssistant Conversations show consistent improvements on standard benchmarks over respective base models.\nWe release our code\\footnote{\\git} and data\\footnote{\\data} under a fully permissive licence.","url_abs":"https://openreview.net/forum?id=VSJotgbPHF","url_pdf":"https://openreview.net/pdf?id=VSJotgbPHF","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":"openassistant-conversations-democratizing-1","repo_url":"https://github.com/laion-ai/open-assistant","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}