1 citations · 2 across the 15 of their papers we have counts for
17 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…
How Do Uncertainty Estimators Align with Hallucination Occurrence in LLMs?
Yedidia Agnimo, Anna Korba, Annabelle Blangero +2
Large language models (LLMs) can hallucinate, but do model uncertainty estimators reliably reveal when they do? Although uncertainty estimators are increasingly used to identify un…
TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models
Duong Nguyen, Mohammed Jawhar, Nicolas Chesneau
Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance through in-context learning, but their in…
CausalProfiler: Generating Synthetic Benchmarks for Rigorous and Transparent Evaluation of Causal Machine Learning
Panayiotis Panayiotou, Audrey Poinsot, Alessandro Leite +3
Causal machine learning (Causal ML) aims to answer "what if" questions using machine learning algorithms, making it a promising tool for high-stakes decision-making. Yet, empirical…
Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption
Audrey Poinsot, Panayiotis Panayiotou, Alessandro Leite +3
Causal machine learning has the potential to revolutionize decision-making by combining the predictive power of machine learning algorithms with the theory of causal inference. How…
Foundation models for time series forecasting: Application in conformal prediction
Sami Achour, Yassine Bouher, Duong Nguyen +1
The zero-shot capabilities of foundation models (FMs) for time series forecasting offer promising potentials in conformal prediction, as most of the available data can be allocated…
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…
Magazine Supply Optimization: a Case-study
Duong Nguyen, Ana Ulianovici, Sami Achour +2
Supply optimization is a complex and challenging task in the magazine retail industry because of the fixed inventory assumption, irregular sales patterns, and varying product and p…
Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges
Audrey Poinsot, Alessandro Leite, Nicolas Chesneau +2
This paper provides a comprehensive review of deep structural causal models (DSCMs), particularly focusing on their ability to answer counterfactual queries using observational dat…
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…
ClimateQ&A: Bridging the gap between climate scientists and the general public
Natalia De La Calzada, Théo Alves Da Costa, Annabelle Blangero +1
This research paper investigates public views on climate change and biodiversity loss by analyzing questions asked to the ClimateQ&A platform. ClimateQ&A is a conversational agent…
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…
Detecting Parts for Action Localization
Nicolas Chesneau, Grégory Rogez, Karteek Alahari +1
In this paper, we propose a new framework for action localization that tracks people in videos and extracts full-body human tubes, i.e., spatio-temporal regions localizing actions,…