2024 Research Publications
Our 2024 publications, each with a citable URL and open underlying datasets. Listings below are illustrative placeholders pending publication.
Last updated: 2026-06-16.
Papers
- Q4 2024 — ChatGPT Censorship Trends Analysis. Refusal-rate movement across the year for GPT-4o/GPT-4, with version attribution. See live data: ChatGPT monitoring.
- Q3 2024 — Comparative Bias Study Across LLMs. Side-by-side bias and refusal profiles for the major models. See the compare hub.
- Q2 2024 — Regional Variation in AI Responses. How responses vary by region, strongest in Gemini.
2024 highlights
- Rising censorship — average refusal rates increased across major models (illustrative).
- Policy convergence — models trended toward similar restriction profiles.
- Silent updates — a majority of behavioral changes shipped unannounced.
- Regional variation — Gemini showed the strongest geographic differences.
Figures are illustrative placeholders, not live measurements. Every published number links to its dataset and sample size. Methodology: monitoring methodology.
How to cite
Use the citation block on each paper. Dataset citations are on the datasets page. To request data or propose review, see collaborations.
GPTfake