collaborators

5 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.CL2026

NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment

Milan Bhan, Jean-Noel Vittaut, Nicolas Chesneau +2

Large Language Models (LLMs) can generate plausible free text self-explanations to justify their answers. However, these natural language explanations may not accurately reflect th…

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…

cs.CL2025

Towards Achieving Concept Completeness for Textual Concept Bottleneck Models

Milan Bhan, Yann Choho, Pierre Moreau +3

Textual Concept Bottleneck Models (TCBMs) are interpretable-by-design models for text classification that predict a set of salient concepts before making the final prediction. This…

cs.CL2025

Mitigating Text Toxicity with Counterfactual Generation

Milan Bhan, Jean-Noel Vittaut, Nina Achache +5

Toxicity mitigation consists in rephrasing text in order to remove offensive or harmful meaning. Neural natural language processing (NLP) models have been widely used to target and…