MétaCan
Menu
Back to cohort
Record W4412373306 · doi:10.56553/popets-2025-0122

An Analysis of Chinese Censorship Bias in LLMs

2025· article· en· W4412373306 on OpenAlexaff
Mohamed Serry, Jeffrey Knockel, Rachel Greenstadt

Bibliographic record

VenueProceedings on Privacy Enhancing Technologies · 2025
Typearticle
Languageen
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsCensorshipPsychologyPolitical scienceLaw

Abstract

fetched live from OpenAlex

When a large language model (LLM) has been trained on text featuring social biases, those biases implicitly impact the outputs of the model. Training an LLM on sanitized content, i.e., those pieces of content which remain after being subjected to state censorship (including alterations, deletions, and self-imposed censorship), results in what we term censorship bias. A model impacted by censorship bias may be less likely to reflect views that are routinely prohibited and more likely to reflect views that are not. This may particularly be an issue when interfacing with a model in a language that is predominantly used in a region with strong censorship laws. In this work, we outline what censorship bias is, introduce a novel methodology for identifying and measuring it, and apply that methodology to evaluate the most popular current LLMs. As part of the contributions of this work we designed and evaluated CensorshipDetector, a Chinese language text classification model which we use as part of our experimental design. Our evaluation of CensorshipDetector found it to be 91% accurate at differentiating between sanitized content and non-sanitized content. Our testing revealed evidence of censorship bias across all of the models we evaluated. Finally, we outline the potential harms of censorship bias, namely the exportation of information manipulation that would have primarily harmed a domestic audience to diaspora, as well as recommendations to various stakeholders to limit the harms of censorship bias and prevent it in the future.

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)0.018
metaresearch head score (Gemma)0.073
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.018
Threshold uncertainty score0.096

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0180.073
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0010.002
Scholarly communication0.0020.003
Open science0.0010.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0020.001

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 head0.044
GPT teacher head0.395
Teacher spread0.350 · 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 designObservational
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
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueProceedings on Privacy Enhancing TechnologiesSame topicComputational and Text Analysis MethodsFrench-language works237,207