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...
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
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
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
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
🎉 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
📦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
🔥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)
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
🥳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) 🤗