{"id":12825,"date":"2026-10-06T09:00:12","date_gmt":"2026-10-06T07:00:12","guid":{"rendered":"https:\/\/talentimpulse.cea.fr\/offre-emploi\/stage-steering-llm-to-inhibit-biases-saclay-h-f\/"},"modified":"2026-11-16T18:45:21","modified_gmt":"2026-11-16T17:45:21","slug":"stage-steering-llm-to-inhibit-biases-saclay-h-f","status":"publish","type":"offre-emploi","link":"https:\/\/talentimpulse.cea.fr\/en\/offre-emploi\/stage-steering-llm-to-inhibit-biases-saclay-h-f\/","title":{"rendered":"Stage Steering LLM to inhibit biases- Saclay-H\/F"},"content":{"rendered":"<p>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 Cl\u00e9ment 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\u00a0: Conduct a literature review on methods for bias in inhibition in multimodal LLMs with steering\u00a0 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\u00a0 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, Herv\u00e9 Le Borgne, Romaric Besan\u00e7on 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<\/p>","protected":false},"featured_media":0,"template":"","categories":[166],"tags":[],"class_list":["post-12825","offre-emploi","type-offre-emploi","status-publish","hentry","category-intelligence-artificielle-et-data-intelligence"],"acf":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/offre-emploi\/12825","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/offre-emploi"}],"about":[{"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/types\/offre-emploi"}],"wp:attachment":[{"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/media?parent=12825"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/categories?post=12825"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/talentimpulse.cea.fr\/en\/wp-json\/wp\/v2\/tags?post=12825"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}