Stage Steering Llm To Inhibit Biases- Saclay H/F CEA
- Saclay - 91
- Stage
- 6 mois
- Industrie high-tech • Telecom
Les missions du poste
As an intern at the CEA, you will have the opportunity to work in a world-renowned research environment. Our teams consist of passionate and dedicated experts, providing an environment conducive to learning and collaboration. You will have access to state-of-the-art equipment and top-tier research resources to carry out your assignments. The work performed may potentially lead to a scientific publication.
Context
Through the thesis of Clément Cornet, the team has already developped several approaches of steering and other works in mechanistic interpretability [1,2]. A large part of the work is integrated into a light python library that can serve as basis for the work.
What do we expect from you ?
The intern will work on the following tasks :
- Conduct a literature review on methods for bias in inhibition in multimodal LLMs with steering
- Conduct experiments with available steering approaches to inhibate biases, including a rigorous quantitative evaluation on well chosen models and modalities
- Develop novel approaches to inhibate biases with steering, in particular to determine its strength automatically
- Develop a demonstrator to showcase the work carried out
Depending on the profile and motivation of the intern, the work may lead to a scientific publication and may be pursued with a PhD focused on a similar topic. The person will work in collaboration with Clement Cornet, Hervé Le Borgne, Romaric Besançon and possibly other researchers of the lab, depending on the direction of the work.
[1] Cornet et al (2025) Explaining How Visual, Textual and Multimodal Encoders Share Concepts, CoRR:2507.18512
[2] Cornet et al (2026) The Deleuzian Representation Hypothesis, ICLR
#Cea List
Le profil recherché
Profil:
- Students in their final year of studies (M2 or last year of engineering school)
- Strong foundations in machine learning and deep learning
- Interest in mechanistic interpretability and bias of AI models
- Python proficiency in pytorch
Les avantages
- Télétravail jusqu’à 3 jours par semaine
- 52 jours de congés/RTT
- Possibilité d’aménagement du temps de travail
- Formation personnalisée
- Restauration d’entreprise
- Offre de transport interne et prise en charge Navigo and co,
- Mutuelle d’entreprise avantageuse
- CE (aides vacances, loisirs, frais de garde, scolarité des enfants etc
Les étapes de recrutement
Les étapes de recrutement peuvent varier selon l'offre à laquelle vous postulez.
-
Dépôt de CV via notre site carrière
-
Préqualification téléphonique
-
Entretiens et évaluation avec manager et RH
-
Négociation salariale et contrat de travail
-
Embauche et intégration
-
CEA en images
Publiée le 01/10/2026 - Réf : 2026-41862