MétaCan
Menu
Back to cohort
Record W4406334158 · doi:10.1038/s42256-024-00969-6

Investigating machine moral judgement through the Delphi experiment

2025· article· en· W4406334158 on OpenAlexaff
Liwei Jiang, Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jenny T. Liang, Sydney Levine, Jesse Dodge, Keisuke Sakaguchi, Maxwell Forbes, Jack Hessel, Jon Borchardt, Taylor Sorensen, Saadia Gabriel, Yulia Tsvetkov, Oren Etzioni, Maarten Sap, Regina Rini, Yejin Choi

Bibliographic record

VenueNature Machine Intelligence · 2025
Typearticle
Languageen
FieldNeuroscience
TopicPsychology of Moral and Emotional Judgment
Canadian institutionsYork University
FundersNaval Information Warfare Center PacificDefense Advanced Research Projects AgencyAllen Institute for Artificial Intelligence
KeywordsMoralityJudgementDelphiDelphi methodComputer scienceArtificial intelligenceEngineering ethicsPsychologyEpistemologyEngineeringPhilosophy

Abstract

fetched live from OpenAlex

As our society adopts increasingly powerful artificial intelligence (AI) systems for pervasive use, there are growing concerns about machine morality—or lack thereof. Millions of users already rely on the outputs of AI systems, such as chatbots, as decision aids. Meanwhile, AI researchers continue to grapple with the challenge of aligning these systems with human morality and values. In response to this challenge, we build and test Delphi, an open-source AI system trained to predict the moral judgements of US participants. The computational framework of Delphi is grounded in the framework proposed by the prominent moral philosopher John Rawls. Our results speak to the promises and limits of teaching machines about human morality. Delphi demonstrates improved generalization capabilities over those exhibited by off-the-shelf neural language models. At the same time, Delphi’s failures also underscore important challenges in this arena. For instance, Delphi has limited cultural awareness and is susceptible to pervasive biases. Despite these shortcomings, we demonstrate several compelling use cases of Delphi, including its incorporation as a component within an ensemble of AI systems. Finally, we computationally demonstrate the potential of Rawls’s prospect of hybrid approaches for reliable moral reasoning, inspiring future research in computational morality. Aligning artificial intelligence systems with human morality poses scientific, societal and ethical challenges. Delphi, an artificial intelligence system designed to predict human moral judgements based on John Rawls’s philosophical framework, is developed and tested, highlighting its potential for ethical applications and emphasizing the need to address its limitations and biases.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.029
metaresearch head score (Gemma)0.111
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.029
Threshold uncertainty score0.155

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0290.111
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0030.004
Scholarly communication0.0030.005
Open science0.0020.005
Research integrity0.0030.006
Insufficient payload (model declined to judge)0.0110.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.079
GPT teacher head0.353
Teacher spread0.275 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designQualitative
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations23
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueNature Machine IntelligenceSame topicPsychology of Moral and Emotional JudgmentFrench-language works237,207