1 citations · 2 across the 7 of their papers we have counts for
10 papers
The Standardization Trap: Certifying Joint Label Processing in Tabular Foundation Models
Duong Nguyen, Nicolas Chesneau, Milan Bhan
Linear regression and kernel smoothing offer tractable explanations of in-context learning: in both, the features determine the weight assigned to each context label. However, whet…
TICDA: Tabular In-Context Data Attribution
Yacine Benihaddadene, Milan Bhan, Eliot Dugelay +4
Tabular foundation models (TFMs) achieve strong predictive performance by conditioning on labeled demonstrations provided in context, without any parameter update. Yet how individu…
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,…
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…
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…
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…
Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations
Milan Bhan, Jean-Noel Vittaut, Nicolas Chesneau +1
Incorporating natural language rationales in the prompt and In-Context Learning (ICL) have led to a significant improvement of Large Language Models (LLMs) performance. However, ge…
TIGTEC : Token Importance Guided TExt Counterfactuals
Milan Bhan, Jean-Noel Vittaut, Nicolas Chesneau +1
Counterfactual examples explain a prediction by highlighting changes of instance that flip the outcome of a classifier. This paper proposes TIGTEC, an efficient and modular method…
Evaluating self-attention interpretability through human-grounded experimental protocol
Milan Bhan, Nina Achache, Victor Legrand +2
Attention mechanisms have played a crucial role in the development of complex architectures such as Transformers in natural language processing. However, Transformers remain hard t…