Collective Constitutional AI: Aligning a Language Model with Public Input
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons
Bradley, R. A., & Terry, M. E. (1952) · Biometrika · doi:10.2307/2334029 · Cited by 2,412
RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS: THE METHOD OF PAIRED COMPARISONS
BRADLEY, R. A., & TERRY, M. E. (1952) · Biometrika · doi:10.1093/biomet/39.3-4.324 · Cited by 1,434
Taxonomy of Risks posed by Language Models
Weidinger, L., Uesato, J., Rauh, M., Griffin, C., Huang, P.-S., Mellor, J., Glaese, A., Cheng, M., Balle, B., Kasirzadeh, A., et al. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533088 · Cited by 764 · cited 1×
“This question is increasingly urgent as LMs are deployed more broadly and in increasingly diverse contexts, making it more likely that varied risks and harms will manifest [62]; anticipating and mitigating risks and harms is done most effectively in collaboration with affected communities [10, 59].”
BackgroundLearning to summarize from human feedback
Stiennon, N., Ouyang, L., Wu, J., Ziegler, D. M., Lowe, R., Voss, C., Radford, A., Amodei, D., & Christiano, P. (2020) · arXiv · doi:10.48550/arxiv.2009.01325 · Cited by 550
Jacobs, A. Z., & Wallach, H. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445901 · Cited by 362 · cited 5×
“When adjudicating some of the trade-offs in the process we ran, one principle that guided our decision-making was aiming to not bias the resulting constitution (e.g. minimizing editorialization of the principles) to maintain construct validity [32].”
BackgroundMethodInfluentialThe Values Encoded in Machine Learning Research
Birhane, A., Kalluri, P., Card, D., Agnew, W., Dotan, R., & Bao, M. (2021) · arXiv · doi:10.48550/arxiv.2106.15590 · Cited by 317
The Values Encoded in Machine Learning Research
Birhane, A., Kalluri, P., Card, D., Agnew, W., Dotan, R., & Bao, M. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533083 · Cited by 317
Stereotyping Norwegian Salmon: An Inventory of Pitfalls in Fairness Benchmark Datasets
Blodgett, S. L., Lopez, G., Olteanu, A., Sim, R., & Wallach, H. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.81 · Cited by 147 · cited 2×
“Automated metrics may fail to capture the intended harm, for which NLP bias benchmarks have been criticized [13, 14]).”
Background
Cited by
Anthis, J. R., Pauketat, J. V. T., Ladak, A., & Manoli, A. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713329 · Cited by 24
“Ef-fectively addressing public concerns will require working together in combination and in parallel.”
Anthis, J. R., Pauketat, J. V. T., Ladak, A., & Manoli, A. (2024) · arXiv · doi:10.48550/arxiv.2407.08867 · Cited by 24
Russo, G., Nozza, D., Röttger, P., & Hovy, D. (2026) · Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2026.eacl-long.305 · Cited by 19
AI as a constituted system: accountability lessons from an LLM experiment
Nabben, K. (2024) · Data & Policy · doi:10.1017/dap.2024.58 · Cited by 11
The Value of Disagreement in AI Design, Evaluation, and Alignment
Fazelpour, S., & Fleisher, W. (2025) · Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3715275.3732146 · Cited by 10
“Examples include participatory-oriented efforts to address underrepresentation [65], include diverse collectives [57] or center marginalized communities [9] in pluralistic alignment; machine learning methodologies such as soft labeling [89], jury learning [46], and multi-annotator modeling [25];…”
Metadata
- Authors
- Huang, S., Siddarth, D., Lovitt, L., Liao, T. I., Durmus, E., Tamkin, A., & Ganguli, D.
- Venue
- The 2024 ACM Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2024-06-03
- Pages
- 1395-1417
- OpenAlex
- W4399363436
- Cited by
- 76
- References
- 14
- FWCI
- 35.63
- Type
- conference paper
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Collective Constitutional AI: Aligning a Language Model with Public Input. https://app.cochat.ai/papers/10.1145/3630106.3658979
- The paper
- Huang, S., Siddarth, D., Lovitt, L., Liao, T. I., Durmus, E., Tamkin, A., & Ganguli, D. (2024). Collective Constitutional AI: Aligning a Language Model with Public Input. The 2024 ACM Conference on Fairness, Accountability, and Transparency. https://doi.org/10.1145/3630106.3658979
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.