MétaCan
Menu
Back to cohort
Record W4287887283 · doi:10.18653/v1/2022.trustnlp-1.3

Does Moral Code have a Moral Code? Probing Delphi’s Moral Philosophy

2022· article· en· W4287887283 on OpenAlexaff
Kathleen Fraser, Svetlana Kiritchenko, Esma Balkır

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldMathematics
TopicCOVID-19 epidemiological studies
Canadian institutionsNational Research Council Canada
Fundersnot available
KeywordsMoralitySet (abstract data type)Process (computing)DelphiCode (set theory)Computer scienceDelphi methodMoral developmentArtificial intelligencePsychologyEpistemologySocial psychologyProgramming languagePhilosophy

Abstract

fetched live from OpenAlex

In an effort to guarantee that machine learning model outputs conform with human moral values, recent work has begun exploring the possibility of explicitly training models to learn the difference between right and wrong.This is typically done in a bottom-up fashion, by exposing the model to different scenarios, annotated with human moral judgements.One question, however, is whether the trained models actually learn any consistent, higher-level ethical principles from these datasets -and if so, what?Here, we probe the Allen AI Delphi model with a set of standardized morality questionnaires, and find that, despite some inconsistencies, Delphi tends to mirror the moral principles associated with the demographic groups involved in the annotation process.We question whether this is desirable and discuss how we might move forward with this knowledge.

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)0.188
metaresearch head score (Gemma)0.393
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.188
Threshold uncertainty score0.994

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1880.393
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.003
Science and technology studies0.0050.035
Scholarly communication0.0090.015
Open science0.0030.008
Research integrity0.0030.010
Insufficient payload (model declined to judge)0.0060.001

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 head0.362
GPT teacher head0.408
Teacher spread0.047 · 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 designTheoretical or conceptual
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

Citations13
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicCOVID-19 epidemiological studiesFrench-language works237,207