Reliable and Confident Use of LLMs

DESCRIPTION

The emergence of Large Language Models (LLMs) represents a transformative milestone in AI, with applications ranging from natural language processing (NLP) to content generation and decision support systems in many areas such as software development, healthcare, company management, education, etc. As these models become increasingly integrated into critical domains in the industry, their reliability and the confidence with which they are used have become significant concerns.

The Chair Reliable and Confident Use of LLMs addresses these challenges through multidisciplinary research aimed at assessing and enhancing the trustworthiness of LLMs in real-world settings. The chair, currently being developed with the UCA Foundation and the MIAI Cluster, has launched in 2025 with the following two industrial partners CGI and AGEATIS. The chair also aims at bringing together researchers from several laboratories (LIMOS, CLERMA) to explore this topic through different but complementary research axes, in order to study and foster LLM usages.

The chair is currently organized into two thematic axes having their own scientific objectives, namely the ‘Computer Science / Software Engineering Axis’, which integrates three research goals (Software Testing with LLMs, LLM with RAG Confidentiality, LLM with RAG optimization and evaluation) and the ‘Sustainable Management of Companies and Public Organizations Axis’ focused one research goal (Responsible Use of LLMs and Transformation of Roles/Functions), with the flexibility to incorporate additional axes in the future. This structure, completed with periodic meetings and brainstorming will allow the sharing of the results obtained from different scientific disciplines to establish more complete and robust approaches.

ACTIVITIES

The Chair has hired two M2 internships in 2025 to start activities on the ‘Computer Science / Software Engineering Axis’. The chair intends to hire three PhD students and one postdoctoral researcher, for covering the four research goals.

Published on  April 2, 2025
Updated on April 9, 2025