4 papers · 1 filter
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…
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…
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…
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…