{"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/collective-constitutional-ai-aligning-a","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","arxiv_id":"2406.07814","date":"2024-06-12","proceeding":null,"authors":["Saffron Huang","Divya Siddarth","Liane Lovitt","Thomas I. Liao","Esin Durmus","Alex Tamkin","Deep Ganguli"],"abstract":"There is growing consensus that language model (LM) developers should not be the sole deciders of LM behavior, creating a need for methods that enable the broader public to collectively shape the behavior of LM systems that affect them. To address this need, we present Collective Constitutional AI (CCAI): a multi-stage process for sourcing and integrating public input into LMs-from identifying a target population to sourcing principles to training and evaluating a model. We demonstrate the real-world practicality of this approach by creating what is, to our knowledge, the first LM fine-tuned with collectively sourced public input and evaluating this model against a baseline model trained with established principles from a LM developer. Our quantitative evaluations demonstrate several benefits of our approach: the CCAI-trained model shows lower bias across nine social dimensions compared to the baseline model, while maintaining equivalent performance on language, math, and helpful-harmless evaluations. Qualitative comparisons of the models suggest that the models differ on the basis of their respective constitutions, e.g., when prompted with contentious topics, the CCAI-trained model tends to generate responses that reframe the matter positively instead of a refusal. These results demonstrate a promising, tractable pathway toward publicly informed development of language models.","url_abs":"https://arxiv.org/abs/2406.07814v1","url_pdf":"https://arxiv.org/pdf/2406.07814v1.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":"collective-constitutional-ai-aligning-a","repo_url":"https://github.com/saffronh/ccai","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"math","task_name":"Math"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.07814","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}