Low-Resource Bias Evaluation and Mitigation for Large Language Models

When:
28/02/2026 – 01/03/2026 all-day
2026-02-28T01:00:00+01:00
2026-03-01T01:00:00+01:00

Offre en lien avec l’Action/le Réseau : – — –/Doctorants

Laboratoire/Entreprise : SAMOVAR, Télécom SudParis, IP Paris
Durée : 3 Years
Contact : luca.benedetto@telecom-sudparis.eu
Date limite de publication : 2026-02-28

Contexte :

Sujet :
We are offering a PhD Thesis position to perform research on NLP and AI Fairness, in the ACMES Team of the SAMOVAR lab at IP Paris.

In this project, we will work on low-resource techniques for bias detection and mitigation in large language models, across a variety of domains, from education to recommendation systems.

You can find a detailed description of this position at the following link: https://partage.imt.fr/index.php/s/qzGZz4KBCMnsJso

To apply, please reach out to luca.benedetto@telecom-sudparis.eu

Interviews will be held in late January.

Profil du candidat :

Formation et compétences requises :
Candidates are expected to have experience with machine learning in general, and specifically with NLP.

Familiarity with frameworks and libraries such as langchain, vLLM, ollama is preferred.

Adresse d’emploi :
Evry ou Palaiseau (France)

Document attaché : 202601071133_sujetThese_ED626_68505.pdf