MétaCan
Menu
Back to cohort
Record W4414602263 · doi:10.1057/s41599-025-05834-4

LLMs as annotators: the effect of party cues on labelling decisions by large language models

2025· article· en· W4414602263 on OpenAlexaff
Sebastián Vallejo Vera, Hunter Driggers

Bibliographic record

VenueHumanities and Social Sciences Communications · 2025
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsWestern University
FundersUniversität Wien
KeywordsPoliticsStatement (logic)Test (biology)Motivated reasoningReplicate

Abstract

fetched live from OpenAlex

Human coders can be biased. We test whether Large Language Models (LLMs) replicate those biases when used as text annotators. By replicating an experiment conducted by Ennser-Jedenastik and Meyer ( 2018 ), we find evidence that LLMs use political information, and specifically party cues, to evaluate political statements. Not only do LLMs use relevant information to contextualize whether a statement is positive, negative, or neutral based on the party cue, they also reflect the biases of the human-generated data upon which they have been trained. We also find that unlike humans, who are only biased when faced with statements from extreme parties, some LLMs exhibit significant bias even when prompted with statements from center-left and center-right parties. The implications of our findings are discussed in the conclusion.

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)0.106
metaresearch head score (Gemma)0.505
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.894
Threshold uncertainty score0.562

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1060.505
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0020.004
Scholarly communication0.0050.008
Open science0.0020.007
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0040.003

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 head0.076
GPT teacher head0.343
Teacher spread0.267 · 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.

Study designSimulation or modeling
DomainMethods
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

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueHumanities and Social Sciences CommunicationsSame topicTopic ModelingFrench-language works237,207