iiinova — where your digital self keeps evolving

Fanny Jourdan @fannyjrd.bsky.social · 27/06/2026

Interpreto is an open-source tool developed as part of the DEEL and FOR projects, with support from IRT Saint Exupéry and ANITI. A big thank you to everyone who attended the tutorial and for the engaging discussions! 4/4

100

Fanny Jourdan @fannyjrd.bsky.social · 27/06/2026

We've also prepared a hands-on notebook that walks through the entire process, from generating explanations to detecting different types of bias. If you're interested, you can download it and explore the examples yourself! 👇 🔗 github.com/FOR-sight-ai/i… 3/4

github.com

200

Fanny Jourdan @fannyjrd.bsky.social · 27/06/2026

During the tutorial, we introduced Interpreto, our open-source library, and demonstrated how explainability methods can help identify and better understand potential biases in NLP models. 2/4

101

Fanny Jourdan @fannyjrd.bsky.social · 27/06/2026

Today, with @antoninpoche.bsky.social, we had the pleasure of presenting a tutorial at @facct.bsky.social on how explainability can be used as a practical tool for fairness analysis. 1/4

190

Reposted by Fanny Jourdan

Antonin Poché @antoninpoche.bsky.social · 23/01/2026

Pleasently surprised to see our blog post trending on HuggingFace 🤗 Well, @fannyjrd.bsky.social did a great job! 🚀 If you missed it, check it out: huggingface.co/blog/Fannyjr... It's a didactic presentation of our new library: 🪄 Interpreto: github.com/FOR-sight-ai...

131

Fanny Jourdan @fannyjrd.bsky.social · 20/01/2026

Thank you to IRT Saint Exupery and ANITI for believing in this project and supporting the vision of fairer and more transparent AI. Interpreto is just getting started, more features, methods, and benchmarks will follow in 2026. Stay tuned for updates! #XAI #LLMs #mechanisticinterpretability 5/5

010

Fanny Jourdan @fannyjrd.bsky.social · 20/01/2026

Thank you to all contributors : Thomas Mulor, @gsarti.com , Frederic Boisnard, Corentin Friedrich, Charlotte Claye, François Hoofd, Raphael Bernas, Céline Hudelot 🙏 And a special thanks to @antoninpoche.bsky.social for his hard work which made this project possible. 👏 4/5

110

Fanny Jourdan @fannyjrd.bsky.social · 20/01/2026

I wanted to make XAI accessible, not just for researchers, but for devs and practitioners too. Because interpretability is key to building transparent and trustworthy AI. My dream? That Interpreto becomes the scikit-learn of explainability. 3/5

110

Fanny Jourdan @fannyjrd.bsky.social · 20/01/2026

What’s in Interpreto? 🔍 Attribution-based & concept-based explainability methods 📏 Evaluation metrics for explanation quality 🤗 Hugging Face integration 💻 Easy install: pip install interpreto 2/5

110

Fanny Jourdan @fannyjrd.bsky.social · 20/01/2026

🎉 I’m thrilled to announce the release of Interpreto: a user-friendly, open-source toolbox to make NLP model interpretability accessible, practical, and rigorous. github.com/FOR-sight-ai... 🧵1/5

github.com

GitHub - FOR-sight-ai/interpreto: 🪄 Interpreto is an interpretability toolbox for LLMs

🪄 Interpreto is an interpretability toolbox for LLMs - FOR-sight-ai/interpreto

171

Reposted by Fanny Jourdan

Antonin Poché @antoninpoche.bsky.social · 20/01/2026

📦You can find the library on GitHub: github.com/FOR-sight-ai... 📚Access the documentation: for-sight-ai.github.io/interpreto/ ⏬Download with pip: `uv pip install interpreto` 📰Look at our paper: arxiv.org/abs/2512.097... 🤗 Check our Huggingface blog post: huggingface.co/blog/Fannyjr... 8/8

github.com

GitHub - FOR-sight-ai/interpreto: 🪄 Interpreto is an interpretability toolbox for LLMs

🪄 Interpreto is an interpretability toolbox for LLMs - FOR-sight-ai/interpreto

041

Reposted by Fanny Jourdan

Antonin Poché @antoninpoche.bsky.social · 20/01/2026

🔥I am super excited for the official release of an open-source library we've been working on for about a year! 🪄interpreto is an interpretability toolbox for HF language models🤗. In both generation and classification! Why do you need it, and for what? 1/8 (links at the end)

1229

Fanny Jourdan @fannyjrd.bsky.social · 19/09/2025

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! 🤩

010

Fanny Jourdan @fannyjrd.bsky.social · 19/09/2025

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

100

Fanny Jourdan @fannyjrd.bsky.social · 19/09/2025

📢 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! 🍁✨

370

Reposted by Fanny Jourdan

Daniel Anadria @danadria.bsky.social · 18/05/2025

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...

041

Reposted by Fanny Jourdan

Antonin Poché @antoninpoche.bsky.social · 16/05/2025

🔥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:

141

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

🙏 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

000

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

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

110

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

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

100

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

🔍 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

100

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

📊 Results: male translations lead, female trail, inclusive dead last—in every configuration. Bias is systemic, not model‑specific. 7/11

100

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

🛠️ 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

100

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

🌈 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

100

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

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

100

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

📦 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

100

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

🤔 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

100

Fanny Jourdan @fannyjrd.bsky.social · 23/04/2025

🥳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

arxiv.org

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...

141

Reposted by Fanny Jourdan

Tom Aarsen @tomaarsen.com · 10/03/2025

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 🧵

57820

Fanny Jourdan @fannyjrd.bsky.social · 25/02/2025

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! 🧐

170

Fanny Jourdan @fannyjrd.bsky.social · 23/02/2025

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

020

Fanny Jourdan @fannyjrd.bsky.social · 31/01/2025

🚨 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 🥹

062

Reposted by Fanny Jourdan

Antonin Poché @antoninpoche.bsky.social · 31/01/2025

🚀 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

662

Fanny Jourdan @fannyjrd.bsky.social · 25/01/2025

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

020

Fanny Jourdan @fannyjrd.bsky.social · 25/01/2025

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

130

Fanny Jourdan @fannyjrd.bsky.social · 24/01/2025

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. 👀

010

Reposted by Fanny Jourdan

Antonin Poché @antoninpoche.bsky.social · 24/01/2025

🤩 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. 🚀

062

Fanny Jourdan @fannyjrd.bsky.social · 16/01/2025

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! 😀

000

Fanny Jourdan @fannyjrd.bsky.social · 16/01/2025

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!

100

Fanny Jourdan @fannyjrd.bsky.social · 16/01/2025

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.

100

Fanny Jourdan @fannyjrd.bsky.social · 16/01/2025

9/ Before starting a PhD, professors often ask students to do a few months' internship or research project in their lab. This allows both sides to evaluate whether the fit is right before committing to the full PhD.

100

Fanny Jourdan @fannyjrd.bsky.social · 16/01/2025

8/ A Master’s degree is usually required to apply for a PhD in Europe. This is because European PhDs are shorter (3-4 years).

100

Fanny Jourdan @fannyjrd.bsky.social · 16/01/2025

7/ In Europe (especially in France), most Master's students applying for PhDs haven’t published papers yet. Prof care more about your motivation and how well you fit their research. Being hardworking, enthusiastic, and pleasant to work with is more valued than having a perfect CV.

100

Fanny Jourdan @fannyjrd.bsky.social · 16/01/2025

6/ If a professor is impressed by your profile but has no openings, ask if they know other colleagues with opportunities. Networking is powerful in academia!

100

Fanny Jourdan @fannyjrd.bsky.social · 16/01/2025

5/ Don’t fake your interest. If you mention a paper you haven’t read, the professor will notice quickly, and it could ruin your chances. Be genuine and show your understanding of their work.

100

Fanny Jourdan @fannyjrd.bsky.social · 16/01/2025

4/ If you don’t get a reply after 1-2 weeks, don’t hesitate to send a polite follow-up (and you can do this several times). Persistence shows interest, but keep it respectful—don’t spam them.

100