Fanny Jourdan

Thanks a lot !

Merci Gabriele ! 😀

I remain affiliated with IRT Saint Exupéry in Toulouse, with the goal of strengthening collaborations between the Montréal and Toulouse AI ecosystems.

Looking forward to this new chapter and all the exchanges ahead! 🤩

Huge thanks to Jackie Chi Kit Cheung (Mila) and Pablo Piantanida (ÉTS) for the invitation 🙏

📢 Life update:
I’m now a visiting researcher at @mila-quebec.bsky.social and @etsmtl.bsky.social in Montréal for the next year and a half! 🍁✨

Recent work had me go off on a tangent mapping the governance structure for clinical decision support systems operating in the European single market.

Here's more info: danadria.com/posts/2025/0...

🔥ConSim has been accepted to the #ACL2025 main conference!

🙏 Thanks again to my amazing co-authors: @alon_jacovi, Agustin Picard, @VictorBoutin, and @Fannyjrd_.

Work done in DEEL and FOR from IRT St Exupéry and @ANITI_Toulouse.

See you in Vienna 📅

For more information, check out my last post:

🙏 Huge thanks to my co‑authors Yannick Chevalier, Cécile Favre and the FOR and DEEL projects in ANITI.
📅 Catch us in Athens on 23-26 June at #FAccT: Let’s chat about fair & inclusive MT.

Merci & see you soon! 🚀

11/11

#NLP #Fairness #LLMs

Everything is open access:

📁 Paper → arxiv.org/abs/2504.15941
📁 Dataset → huggingface.co/datasets/Fan...
📂 Code → github.com/fanny-jourda...

✨ Test your model, compare, fork, or build on top. Let’s fix MT together.

10/11

Prompting helps: moral + linguistic prompts increase inclusive outputs and reduce the male-female gap. But it's no silver bullet: quality can drop, and even the best setup yields proper 🇫🇷 markers (like iel or un.e) in only ≤11% of inclusive cases. We need more than vibes.

9/11

🔍 Singular “they” is hardest. In 246 test cases, models output plural “ils/elles” 50–90 % of the time or gendered “il/elle”. Even with inclusive prompts, “iel” appears only sporadically. Diagnostics matter!

8/11

📊 Results: male translations lead, female trail, inclusive dead last—in every configuration. Bias is systemic, not model‑specific.

7/11

🛠️ Benchmarked Gemma‑2B, Mistral‑7B, Llama 3‑8B & 70B under 4 prompts (baseline, moral, linguistic, moral+ling). Metrics: BLEU, COMET and a custom pronoun/agreement checker → 16 slices x 2 scores = deep bias audit!

6/11

🌈 Inclusive forms follow consistent 🇫🇷 conventions:

• Pronouns: iel (=singular they)

• Determiners: un.e (=a), lea (=the)

• Nouns: étudiant.e (=student), etc.

✅We also provide a mapping dictionary so alternate spellings are valid.

Everything’s open-source (🤗 + GitHub)!

5/11

Each entry includes:
•Gender: male/female/inclusive → each sentence exists in 3 versions for counterfactual eval
•Ambiguity: ambiguous/unambiguous/long unambiguous → tests contextual understanding
•Stereotype: masc/fem/neutral job → tests stereotype bias
•Occupation: 🇫🇷 masc/fem/incl forms

4/11

📦 FairTranslate contains 2 418 EN‑FR sentence pairs covering 62 occupations. Every example appears in three gender variants (male, female, inclusive) and carries metadata on stereotype, ambiguity type, and more. All human‑annotated for reliability.

3/11

🤔 Most benchmarks for gender bias in machine translation focus on binary gender (male/female). FairTranslate introduces a new resource for evaluating how LLMs handle non-binary gender in English→French, a language where gender is deeply grammaticalized.

2/11

FairTranslate: An English-French Dataset for Gender Bias Evaluation in Machine Translation by Overcoming Gender Binarity Large Language Models (LLMs) are increasingly leveraged for translation tasks but often fall short when translating inclusive language -- such as texts containing the singular 'they' pronoun or otherw...

🥳Our paper “FairTranslate: An English-French Dataset for Gender Bias Evaluation in Machine Translation by Overcoming Gender Binarity” (arxiv.org/abs/2504.15941) was accepted at #FAccT2025! This 🧵 covers our new dataset and what it reveals about persistent bias in LLMs. 👇
1/11

An assembly of 18 European companies, labs, and universities have banded together to launch 🇪🇺 EuroBERT!

It's a state-of-the-art multilingual encoder for 15 European languages, designed to be finetuned for retrieval, classification, etc.

Details in 🧵

An incredible collaboration is on the way… and it will soon give birth to an exciting new toolbox! But no spoilers for now. Stay tuned! 🧐

Very interesting study! (and your name is very pretty too) 🤗

🚨 New #XAI paper alert!

With the amazing @antoninpoche.bsky.social, Alon Jacovi, Agustin Picard, and
@victorboutin.bsky.social we’ve developed a framework to evaluate concept-based explanations in #NLP ! 📊

So proud of my first PhD student's first paper 🥹

🚀 Thrilled to share our new paper (the first of my PhD)!

How can we compare concept-based #XAI methods in #NLProc?

ConSim (arxiv.org/abs/2501.05855) provides the answer.

Read the thread to find out which method is the most interpretable! 🧵1/7

Not so far from my original goal (and finally I'm happy because I'm having a more concrete impact). 🙌

if you went to college
1. what was your career goal when you started?
2. your initial major?
3. if you changed majors, what did you change to?
4. what do you do now, professionally?

1. Researcher in fundamental mathematics
2. Fundamental mathematics
3. Applied mathematics
4. AI/NLP researcher

Super happy to co-supervising the PhD of someone as brillant as @antoninpoche.bsky.social ! 🥰
You should definitely follow him, an exciting #XAI paper is coming soon. 👀

🤩 Thrilled to announce that I've started my PhD in
#XAI for #NLProc under the supervision of Pr. Nicholas Asher,
@philmuller.bsky.social, and @fannyjrd.bsky.social!

My project? Improve the transparency of LLMs through interactive explanations and user-tailored explanations. 🚀

Professors prefer students who are reliable, motivated, and easy to work with over those with a perfect academic record. Show that you’re passionate and serious about their work, and you’ll stand out.
Good luck with your PhD search! 😀

11/ PhD opportunities in Europe aren’t tied to specific academic cycles. You can apply for a PhD at any time during the year. It will depend on when professors have funding available for new students, so be proactive in reaching out!

10/ You don’t need to speak the local language; almost all PhD programs can be done in English, even in non-English-speaking countries.