2 papers
cs.CV2026
Towards Faithful Multimodal Concept Bottleneck Models
Pierre Moreau, Emeline Pineau Ferrand, Yann Choho +3
Concept Bottleneck Models (CBMs) are interpretable models that route predictions through a layer of human-interpretable concepts. While widely studied in vision and, more recently,…
cs.CL2025
In-Distribution Steering: Balancing Control and Coherence in Language Model Generation
Arthur Vogels, Benjamin Wong, Yann Choho +2
Activation steering methods control large language model (LLM) behavior by modifying internal activations at inference time. However, most existing activation steering methods rely…