Mighty Morphin Power Rangers

New policy blogpost! The EU is speaking a lot about sovereignty. A cornerstone of digital sovereignty is and has to be open source.
As AI becomes more central to everything from public services to national security, the ability to govern, adapt, and understand these systems is no longer optional. Sovereign control over data, infrastructure, technology, and regulation is vital, and open source AI provides the foundation.
In my latest blog post, I explore how open source:
✅ Enables democratic oversight
✅ Reduces dependency on foreign platforms
✅ Supports regional innovation and infrastructure
✅ Advances regulatory and technological sovereignty
🛠 From small transparent models like OLMo2 to tools like Hugging Face Transformers or Sarvam-M for Indian languages, open source efforts are already powering sovereign AI ecosystems worldwide.
🔎 Read more about how open source AI is reshaping autonomy, innovation, and trust in the digital age:
👉 https://huggingface.co/blog/frimelle/sovereignty-and-open-source
with @yjernite

Shayne

authored a paper 3 months ago

The Leaderboard Illusion

Paper • 2504.20879 • Published Apr 29 • 70

frimelle

authored 2 papers 6 months ago

Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions

Paper • 2310.05779 • Published Oct 9, 2023 • 1

Presumed Cultural Identity: How Names Shape LLM Responses

Paper • 2502.11995 • Published Feb 17 • 11

frimelle

posted an update 6 months ago

Post

2457

What’s in a name? More than you might think, especially for AI.
Whenever I introduce myself, people often start speaking French to me, even though my French is très basic. It turns out that AI systems do something similar:
Large language models infer cultural identity from names, shaping their responses based on presumed backgrounds. But is this helpful personalization or a reinforcement of stereotypes?
In our latest paper, we explored this question by testing DeepSeek, Llama, Aya, Mistral-Nemo, and GPT-4o-mini on how they associate names with cultural identities. We analysed 900 names from 30 cultures and found strong assumptions baked into AI responses: some cultures were overrepresented, while others barely registered.
For example, a name like "Jun" often triggered Japan-related responses, while "Carlos" was linked primarily to Mexico, even though these names exist in multiple countries. Meanwhile, names from places like Ireland led to more generic answers, suggesting weaker associations in the training data.
This has real implications for AI fairness: How should AI systems personalize without stereotyping? Should they adapt at all based on a name?
Work with some of my favourite researchers: @sidicity Arnav Arora and @IAugenstein
Read the full paper here: Presumed Cultural Identity: How Names Shape LLM Responses (2502.11995)

frimelle

posted an update 6 months ago

Post

533

I was quoted in an article about the French Lucie AI in La Presse. While I love the name for obvious reasons 👀 there were still a lot of problems with the model and how and when it was deployed. Nevertheless seeing new smaller models being developed is an exciting direction for the next years of AI development to come!

https://www.lapresse.ca/affaires/techno/2025-02-02/radioscopie/lucie-l-ia-francaise-qui-ne-passe-pas-le-test.php

Also fun to see my comments in French.

AI & ML interests

Recent Activity

Team members 5

mmpr's activity

[bot] Conversion to Parquet

[bot] Conversion to Parquet

[bot] Conversion to Parquet

[bot] Conversion to Parquet

README

README