ArticleProceedings of the National Academy of Sciences of the United States of America2026
Moral stereotyping in large language models.
Article in Proceedings of the National Academy of Sciences of the United States of America, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 6 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
6 citing papers in PubMed.
- Digital twins are funhouse mirrors: Five systematic distortions.Science advances · 2026Article
- Persona-prompted LLM agents achieve modest but genuine prediction of human social media reactions.Scientific reports · 2026Article
- From Alliance to Nexus: Rethinking Digital Therapeutic Relationships.JMIR mental health · 2026Article
- Moral stereotyping in large language models.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
- A benchmark dataset for evaluating gender sensitivity in Korean political discourse with large language models.Scientific data · 2025Article
- Measuring gender and racial biases in large language models: Intersectional evidence from automated resume evaluation.PNAS nexus · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
Abstract
Can Large Language Models (LLMs) accurately estimate various societies' moral values? Here, we query the perceptions of LLMs regarding the moral norms of the "average" person from 48 nations and compare them to a large-scale ([Formula: see text]) survey of six moral values (Care, Equality, Proportionality, Loyalty, Authority, and Purity) from those populations. Our findings indicate that LLMs poorly capture the moral diversity around the globe, systematically overestimating some moral values (particularly Care) and underestimating others (especially Purity). Notably, examining various versions of Generative Pre-trained Transformer (GPT) shows that these LLMs may overestimate the overall moral concerns of some Western countries (e.g., the United States, Canada, and Australia) while underestimating those of non-Western countries (e.g., Nigeria, Morocco, and Indonesia). Our work demonstrates that LLMs are inaccurate generators of cross-cultural estimations in the moral domain; in other words, they stereotype the moral values of non-Western populations in predictable ways. Our results highlight the ethical and epistemic risks of relying on LLMs to estimate the endorsement of moral values around the globe.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.