MétaCan
Menu
← Back to cohort
Record W4388184389 · doi:10.48550/arxiv.2310.20059

Concept Alignment as a Prerequisite for Value Alignment

2023· preprint· en· W4388184389 on OpenAlexfundno aff
Sunayana Rane, Mark K. Ho, Ilia Sucholutsky, Thomas L. Griffiths

Bibliographic record

VenuearXiv (Cornell University) · 2023
Typepreprint
Languageen
FieldNeuroscience
TopicPsychology of Moral and Emotional Judgment
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceValue (mathematics)Artificial intelligenceRepresentation (politics)Human–computer interactionMachine learning

Abstract

fetched live from OpenAlex

Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently using to understand and evaluate what happens in the world. The dependence of values on concepts means that concept alignment is a prerequisite for value alignment -- agents need to align their representation of a situation with that of humans in order to successfully align their values. Here, we formally analyze the concept alignment problem in the inverse reinforcement learning setting, show how neglecting concept alignment can lead to systematic value mis-alignment, and describe an approach that helps minimize such failure modes by jointly reasoning about a person's concepts and values. Additionally, we report experimental results with human participants showing that humans reason about the concepts used by an agent when acting intentionally, in line with our joint reasoning model.

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)0.010
metaresearch head score (Gemma)0.057
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 score0.010
Threshold uncertainty score0.055

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0100.057
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0020.006
Scholarly communication0.0040.014
Open science0.0020.005
Research integrity0.0030.005
Insufficient payload (model declined to judge)0.0070.001

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 head0.260
GPT teacher head0.252
Teacher spread0.008 · 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

Citations2
Published2023
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)→Same topicPsychology of Moral and Emotional Judgment→French-language works237,207→