ArticleScience advances2025
Source framing triggers systematic bias in large language models.
Article in Science advances, 2025. 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.
- The 42 problem in AI-assisted research.eLife · 2026Article
- AI safety is a system property, not a sum of individual defenses.Patterns (New York, N.Y.) · 2026Review
- Selective divergence between Grokipedia and Wikipedia articles.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
- The sophist in the server : Rhetoric, Reasoning and Scientific Judgment in the Age of LLMs.EMBO reports · 2026Article
- Personas Shift Clinical Action Thresholds in Large Language Models.medRxiv : the preprint server for health sciences · 2026Article
- Detecting FIMI: A methodological framework for testing OSINT tools in TTPs detection.Open research Europe · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Large language models (LLMs) are increasingly used to evaluate text, raising urgent questions about whether their judgments are consistent, unbiased, and robust to framing effects. Here, we examine inter- and intramodel agreement across four state-of-the-art LLMs tasked with evaluating 4800 narrative statements on 24 different topics of social, political, and public health relevance, for a total of 192,000 assessments. We manipulate the disclosed source of each statement to assess how attribution to either another LLM or a human author of specified nationality affects evaluation outcomes. Different LLMs display a remarkably high degree of inter- and intramodel agreement across topics, but this alignment breaks down when source framing is introduced. Attributing statements to Chinese individuals systematically lowers agreement scores across all models and, in particular, for DeepSeek Reasoner. Our findings show that LLMs' own judgment of agreement with narrative statements exhibit systematic bias from framing effects, with substantial implications for the neutrality and fairness of LLM-mediated information systems.
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.