Nicolas Chesneau

Yedidia Agnimo, Anna Korba, Annabelle Blangero et al.

Large language models (LLMs) are prone to hallucinations, i.e., statements unsupported by the input or training data, hindering reliable deployment. In parallel, numerous uncertainty estimation (UE) methods have been proposed to quantify model confidence and are often implicitly treated as proxies for model failure. However, the relationship between uncertainty and hallucinations remains insufficiently characterized. We present a systematic empirical study of the association between uncertainty estimators and hallucinations in LLMs. Rather than assuming this association, we evaluate directly when and to what extent it holds. We consider a diverse set of uncertainty estimators, including information-theoretic, sampling-based, and reflexive estimators, and examine their behavior across hallucination settings. Our experiments cover both intrinsic hallucinations (violations of input faithfulness) and extrinsic hallucinations (unsupported claims relative to training data), using four complementary benchmarks, including RAGTruth and HalluLens. We find that the association is highly variable and often weak, depending on the hallucination type and the LLM under evaluation. These results challenge the use of uncertainty as a direct signal of hallucination and clarify when it provides actionable information.

Milan Bhan, Jean-Noel Vittaut, Nicolas Chesneau et al.

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 for generating sparse, plausible and diverse counterfactual explanations for textual data. TIGTEC is a text editing heuristic that targets and modifies words with high contribution using local feature importance. A new attention-based local feature importance is proposed. Counterfactual candidates are generated and assessed with a cost function integrating semantic distance, while the solution space is efficiently explored in a beam search fashion. The conducted experiments show the relevance of TIGTEC in terms of success rate, sparsity, diversity and plausibility. This method can be used in both model-specific or model-agnostic way, which makes it very convenient for generating counterfactual explanations.

Milan Bhan, Nina Achache, Victor Legrand et al.

Attention mechanisms have played a crucial role in the development of complex architectures such as Transformers in natural language processing. However, Transformers remain hard to interpret and are considered as black-boxes. This paper aims to assess how attention coefficients from Transformers can help in providing interpretability. A new attention-based interpretability method called CLaSsification-Attention (CLS-A) is proposed. CLS-A computes an interpretability score for each word based on the attention coefficient distribution related to the part specific to the classification task within the Transformer architecture. A human-grounded experiment is conducted to evaluate and compare CLS-A to other interpretability methods. The experimental protocol relies on the capacity of an interpretability method to provide explanation in line with human reasoning. Experiment design includes measuring reaction times and correct response rates by human subjects. CLS-A performs comparably to usual interpretability methods regarding average participant reaction time and accuracy. The lower computational cost of CLS-A compared to other interpretability methods and its availability by design within the classifier make it particularly interesting. Data analysis also highlights the link between the probability score of a classifier prediction and adequate explanations. Finally, our work confirms the relevancy of the use of CLS-A and shows to which extent self-attention contains rich information to explain Transformer classifiers.

Duong Nguyen, Ana Ulianovici, Sami Achour et al.

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 point-of-sale characteristics. We introduce AthenIA, an industrialized magazine supply optimization solution that plans the supply for over 20,000 points of sale in France. We modularize the supply planning process into a four-step pipeline: demand sensing, optimization, business rules, and operating. The core of the solution is a novel group conformalized quantile regression method that integrates domain expert insights, coupled with a supply optimization technique that balances the costs of out-of-stock against the costs of over-supply. AthenIA has proven to be a valuable tool for magazine publishers, particularly in the context of evolving economic and ecological challenges.

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 inductive biases remain fixed at inference time. Adapting a pretrained TFM to a specific dataset or task typically requires either full fine-tuning, which is computationally expensive, or parameter-efficient tuning methods (PEFT) such as LoRA, which must be tailored to the internal architecture of each TFM. Furthermore, the evidence on whether weight-space fine-tuning improves accuracy or calibration is mixed \citep{tanna_exploring_2026,rubachev_finetuning_2025}. We introduce TFM-Retouche, a lightweight input-space residual adapter that is architecture-agnostic by design with respect to the frozen TFM backbone. TFM-Retouche learns a small residual correction in the input space to align the input data with the inductive biases of the pretrained model. The adapter is trained end-to-end through the frozen TFM, with a post-training identity guard that falls back to the unmodified TFM whenever adaptation does not help on held-out validation. On TabArena-Lite (51 datasets spanning binary classification, multiclass classification, and regression), TabICLv2-Retouche -- the framework instantiated on TabICLv2 -- is the top-ranked method on the leaderboard with light per-task tuning and ensembling, lifting aggregate Elo by +56 over the frozen TabICLv2 base and sitting on the Pareto front of predictive quality versus both training and inference time.

Milan Bhan, Jean-Noel Vittaut, Nicolas Chesneau et al.

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, generating high-quality rationales require human-annotation or the use of auxiliary proxy models. In this work, we propose Self-AMPLIFY to automatically generate rationales from post hoc explanation methods applied to Small Language Models (SLMs) to improve their own performance. Self-AMPLIFY is a 3-step method that targets samples, generates rationales and builds a final prompt to leverage ICL. Self-AMPLIFY performance is evaluated on four SLMs and five datasets requiring strong reasoning abilities. Self-AMPLIFY achieves good results against competitors, leading to strong accuracy improvement. Self-AMPLIFY is the first method to apply post hoc explanation methods to autoregressive language models to generate rationales to improve their own performance in a fully automated manner.

Audrey Poinsot, Alessandro Leite, Nicolas Chesneau et al.

This paper provides a comprehensive review of deep structural causal models (DSCMs), particularly focusing on their ability to answer counterfactual queries using observational data within known causal structures. It delves into the characteristics of DSCMs by analyzing the hypotheses, guarantees, and applications inherent to the underlying deep learning components and structural causal models, fostering a finer understanding of their capabilities and limitations in addressing different counterfactual queries. Furthermore, it highlights the challenges and open questions in the field of deep structural causal modeling. It sets the stages for researchers to identify future work directions and for practitioners to get an overview in order to find out the most appropriate methods for their needs.

Milan Bhan, Jean-Noel Vittaut, Nina Achache et al.

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 mitigate textual toxicity. However, existing methods fail to detoxify text while preserving the initial non-toxic meaning at the same time. In this work, we propose to apply counterfactual generation methods from the eXplainable AI (XAI) field to target and mitigate textual toxicity. In particular, we perform text detoxification by applying local feature importance and counterfactual generation methods to a toxicity classifier distinguishing between toxic and non-toxic texts. We carry out text detoxification through counterfactual generation on three datasets and compare our approach to three competitors. Automatic and human evaluations show that recently developed NLP counterfactual generators can mitigate toxicity accurately while better preserving the meaning of the initial text as compared to classical detoxification methods. Finally, we take a step back from using automated detoxification tools, and discuss how to manage the polysemous nature of toxicity and the risk of malicious use of detoxification tools. This work is the first to bridge the gap between counterfactual generation and text detoxification and paves the way towards more practical application of XAI methods.

Milan Bhan, Yann Choho, Pierre Moreau et al.

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 paper proposes Complete Textual Concept Bottleneck Model (CT-CBM), a novel TCBM generator building concept labels in a fully unsupervised manner using a small language model, eliminating both the need for predefined human labeled concepts and LLM annotations. CT-CBM iteratively targets and adds important and identifiable concepts in the bottleneck layer to create a complete concept basis. CT-CBM achieves striking results against competitors in terms of concept basis completeness and concept detection accuracy, offering a promising solution to reliably enhance interpretability of NLP classifiers.

Sami Achour, Yassine Bouher, Duong Nguyen et al.

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 to calibration. This study compares the performance of Time Series Foundation Models (TSFMs) with traditional methods, including statistical models and gradient boosting, within a conformal prediction setting. Our findings highlight two key advantages of TSFMs. First, when the volume of data is limited, TSFMs provide more reliable conformalized prediction intervals than classic models, thanks to their superior predictive accuracy. Second, the calibration process is more stable because more data are used for calibration. Morever, the fewer data available, the more pronounced these benefits become, as classic models require a substantial amount of data for effective training. These results underscore the potential of foundation models in improving conformal prediction reliability in time series applications, particularly in data-constrained cases. All the code to reproduce the experiments is available.

Natalia De La Calzada, Théo Alves Da Costa, Annabelle Blangero et al.

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 that uses LLMs to respond to queries based on over 14,000 pages of scientific literature from the IPCC and IPBES reports. Launched online in March 2023, the tool has gathered over 30,000 questions, mainly from a French audience. Its chatbot interface allows for the free formulation of questions related to nature*. While its main goal is to make nature science more accessible, it also allows for the collection and analysis of questions and their themes. Unlike traditional surveys involving closed questions, this novel method offers a fresh perspective on individual interrogations about nature. Running NLP clustering algorithms on a sample of 3,425 questions, we find that a significant 25.8% inquire about how climate change and biodiversity loss will affect them personally (e.g., where they live or vacation, their consumption habits) and the specific impacts of their actions on nature (e.g., transportation or food choices). This suggests that traditional methods of surveying may not identify all existing knowledge gaps, and that relying solely on IPCC and IPBES reports may not address all individual inquiries about climate and biodiversity, potentially affecting public understanding and action on these issues. *we use 'nature' as an umbrella term for 'climate change' and 'biodiversity loss'

Panayiotis Panayiotou, Audrey Poinsot, Alessandro Leite et al.

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 evaluation practices in Causal ML remain limited. Existing benchmarks often rely on a handful of hand-crafted or semi-synthetic datasets, leading to brittle, non-generalizable conclusions. To bridge this gap, we introduce CausalProfiler, a synthetic benchmark generator for Causal ML methods. Based on a set of explicit design choices about the class of causal models, queries, and data considered, the CausalProfiler randomly samples causal models, data, queries, and ground truths constituting the synthetic causal benchmarks. In this way, Causal ML methods can be rigorously and transparently evaluated under a variety of conditions. This work offers the first random generator of synthetic causal benchmarks with coverage guarantees and transparent assumptions operating on the three levels of causal reasoning: observation, intervention, and counterfactual. We demonstrate its utility by evaluating several state-of-the-art methods under diverse conditions and assumptions, both in and out of the identification regime, illustrating the types of analyses and insights the CausalProfiler enables.

Audrey Poinsot, Panayiotis Panayiotou, Alessandro Leite et al.

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. However, these methods remain underutilized by the broader machine learning community, in part because current empirical evaluations do not permit assessment of their reliability and robustness, undermining their practical utility. Specifically, one of the principal criticisms made by the community is the extensive use of synthetic experiments. We argue, on the contrary, that synthetic experiments are essential and necessary to precisely assess and understand the capabilities of causal machine learning methods. To substantiate our position, we critically review the current evaluation practices, spotlight their shortcomings, and propose a set of principles for conducting rigorous empirical analyses with synthetic data. Adopting the proposed principles will enable comprehensive evaluations that build trust in causal machine learning methods, driving their broader adoption and impactful real-world use.

Milan Bhan, Jean-Noel Vittaut, Nicolas Chesneau et al.

Large Language Models (LLMs) can generate plausible free text self-explanations to justify their answers. However, these natural language explanations may not accurately reflect the model's actual reasoning process, indicating a lack of faithfulness. Existing faithfulness evaluation methods rely primarily on behavioral tests or computational block analysis without examining the semantic content of internal neural representations. This paper proposes NeuroFaith, a flexible framework that measures the faithfulness of LLM free text self-explanation by identifying key concepts within explanations and mechanistically testing whether these concepts actually influence the model's predictions. We show the versatility of NeuroFaith across 2-hop reasoning and classification tasks. Additionally, a linear faithfulness probe based on NeuroFaith is developed to detect unfaithful self-explanations from representation space and improve faithfulness through steering. NeuroFaith provides a principled approach to evaluating and enhancing the faithfulness of LLM free text self-explanations, addressing critical needs for trustworthy AI systems.

Nicolas Chesneau, Grégory Rogez, Karteek Alahari et al.

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, even in the case of occlusions or truncations. This is achieved by training a novel human part detector that scores visible parts while regressing full-body bounding boxes. The core of our method is a convolutional neural network which learns part proposals specific to certain body parts. These are then combined to detect people robustly in each frame. Our tracking algorithm connects the image detections temporally to extract full-body human tubes. We apply our new tube extraction method on the problem of human action localization, on the popular JHMDB dataset, and a very recent challenging dataset DALY (Daily Action Localization in YouTube), showing state-of-the-art results.