23 citations · 81 across the 22 of their papers we have counts for
23 papers
Energy Consumption Analysis of Discrete Diffusion and Autoregressive Language Models
Boris Ruf, Marcin Detyniecki
As Large Language Models (LLMs) continue to scale, their energy consumption during inference has become a critical concern. While Autoregressive (AR) models are the industry standa…
The Cost of Context: Profiling the Energy Footprint of Input Tokens in Large Language Models
Boris Ruf, Marcin Detyniecki
The rapid adoption of Retrieval-Augmented Generation (RAG) and long-context LLMs has shifted the computational burden toward the prefill phase---the initial stage where the model p…
Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation
Aniketh Iyengar, Jiaqi Han, Boris Ruf +3
The rapidly growing computational demands of diffusion models for image generation have raised significant concerns about energy consumption and environmental impact. While existin…
Mitigating the Carbon Footprint of Chatbots as Consumers
Boris Ruf, Marcin Detyniecki
In the context of the high energy demand of large language models (LLMs) and growing concerns about global warming, there is significant demand for actionable recommendations that…
The "Huh?" Button: Improving Understanding in Educational Videos with Large Language Models
Boris Ruf, Marcin Detyniecki
We propose a simple way to use large language models (LLMs) in education. Specifically, our method aims to improve individual comprehension by adding a novel feature to online vide…
Why do explanations fail? A typology and discussion on failures in XAI
Clara Bove, Thibault Laugel, Marie-Jeanne Lesot +2
As Machine Learning models achieve unprecedented levels of performance, the XAI domain aims at making these models understandable by presenting end-users with intelligible explanat…
OptiGrad: A Fair and more Efficient Price Elasticity Optimization via a Gradient Based Learning
Vincent Grari, Marcin Detyniecki
This paper presents a novel approach to optimizing profit margins in non-life insurance markets through a gradient descent-based method, targeting three key objectives: 1) maximizi…
On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
Vincent Grari, Thibault Laugel, Tatsunori Hashimoto +2
In the field of algorithmic fairness, significant attention has been put on group fairness criteria, such as Demographic Parity and Equalized Odds. Nevertheless, these objectives,…
Open and Linked Data Model for Carbon Footprint Scenarios
Boris Ruf, Marcin Detyniecki
Carbon footprint quantification is key to well-informed decision making over carbon reduction potential, both for individuals and for companies. Many carbon footprint case studies…
Achieving Diversity in Counterfactual Explanations: a Review and Discussion
Thibault Laugel, Adulam Jeyasothy, Marie-Jeanne Lesot +2
In the field of Explainable Artificial Intelligence (XAI), counterfactual examples explain to a user the predictions of a trained decision model by indicating the modifications to…
When mitigating bias is unfair: multiplicity and arbitrariness in algorithmic group fairness
Natasa Krco, Thibault Laugel, Vincent Grari +2
Most research on fair machine learning has prioritized optimizing criteria such as Demographic Parity and Equalized Odds. Despite these efforts, there remains a limited understandi…
Integrating Prior Knowledge in Post-hoc Explanations
Adulam Jeyasothy, Thibault Laugel, Marie-Jeanne Lesot +2
In the field of eXplainable Artificial Intelligence (XAI), post-hoc interpretability methods aim at explaining to a user the predictions of a trained decision model. Integrating pr…
A Fair Pricing Model via Adversarial Learning
Vincent Grari, Arthur Charpentier, Marcin Detyniecki
At the core of insurance business lies classification between risky and non-risky insureds, actuarial fairness meaning that risky insureds should contribute more and pay a higher p…
Fairness without the sensitive attribute via Causal Variational Autoencoder
Vincent Grari, Sylvain Lamprier, Marcin Detyniecki
In recent years, most fairness strategies in machine learning models focus on mitigating unwanted biases by assuming that the sensitive information is observed. However this is not…
How to choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice
Tom Vermeire, Thibault Laugel, Xavier Renard +2
Explainability is becoming an important requirement for organizations that make use of automated decision-making due to regulatory initiatives and a shift in public awareness. Vari…
Understanding surrogate explanations: the interplay between complexity, fidelity and coverage
Rafael Poyiadzi, Xavier Renard, Thibault Laugel +2
This paper analyses the fundamental ingredients behind surrogate explanations to provide a better understanding of their inner workings. We start our exposition by considering glob…
On the overlooked issue of defining explanation objectives for local-surrogate explainers
Rafael Poyiadzi, Xavier Renard, Thibault Laugel +2
Local surrogate approaches for explaining machine learning model predictions have appealing properties, such as being model-agnostic and flexible in their modelling. Several method…
Explaining how your AI system is fair
Boris Ruf, Marcin Detyniecki
To implement fair machine learning in a sustainable way, choosing the right fairness objective is key. Since fairness is a concept of justice which comes in various, sometimes conf…
Implementing Fair Regression In The Real World
Boris Ruf, Marcin Detyniecki
Most fair regression algorithms mitigate bias towards sensitive sub populations and therefore improve fairness at group level. In this paper, we investigate the impact of such impl…
Understanding Prediction Discrepancies in Machine Learning Classifiers
Xavier Renard, Thibault Laugel, Marcin Detyniecki
A multitude of classifiers can be trained on the same data to achieve similar performances during test time, while having learned significantly different classification patterns. T…
Towards the Right Kind of Fairness in AI
Boris Ruf, Marcin Detyniecki
Fairness is a concept of justice. Various definitions exist, some of them conflicting with each other. In the absence of an uniformly accepted notion of fairness, choosing the righ…
On the Granularity of Explanations in Model Agnostic NLP Interpretability
Yves Rychener, Xavier Renard, Djamé Seddah +2
Current methods for Black-Box NLP interpretability, like LIME or SHAP, are based on altering the text to interpret by removing words and modeling the Black-Box response. In this pa…
Fairness-Aware Neural Réyni Minimization for Continuous Features
Vincent Grari, Boris Ruf, Sylvain Lamprier +1
The past few years have seen a dramatic rise of academic and societal interest in fair machine learning. While plenty of fair algorithms have been proposed recently to tackle this…