Publications

Understanding Intrinsic Socioeconomic Biases in Large Language Models
Mina Arzaghi
Florian Carichon
Golnoosh Farnadi
Large Language Models (LLMs) are increasingly integrated into critical decision-making processes, such as loan approvals and visa applicatio… (voir plus)ns, where inherent biases can lead to discriminatory outcomes. In this paper, we examine the nuanced relationship between demographic attributes and socioeconomic biases in LLMs, a crucial yet understudied area of fairness in LLMs. We introduce a novel dataset of one million English sentences to systematically quantify socioeconomic biases across various demographic groups. Our findings reveal pervasive socioeconomic biases in both established models such as GPT-2 and state-of-the-art models like Llama 2 and Falcon. We demonstrate that these biases are significantly amplified when considering intersectionality, with LLMs exhibiting a remarkable capacity to extract multiple demographic attributes from names and then correlate them with specific socioeconomic biases. This research highlights the urgent necessity for proactive and robust bias mitigation techniques to safeguard against discriminatory outcomes when deploying these powerful models in critical real-world applications.
2024-05-28
ArXiv (prépublication)
doi.org
arxiv.org
Advancing Cultural Inclusivity: Optimizing Embedding Spaces for Balanced Music Recommendations
Armin Moradi
Nicola Neophytou
Golnoosh Farnadi
2024-05-27
ArXiv (prépublication)
doi.org
arxiv.org
Estimating Expectations without Sampling: Neural Stein Estimation
Mohsin Hasan
Dinghuai Zhang
Cheikh Ahmed
Awa Khouna
Yoshua Bengio
We propose a method for estimating the expected value of a given function …
2024-05-27
approximateinference.org/AABI/2024/Symposium (accepté)
openreview.net
openreview.net
An Introduction to Vision-Language Modeling
Florian Bordes
Richard Yuanzhe Pang
Anurag Ajay
Alexander C. Li
Adrien Bardes
Suzanne Petryk
Oscar Mañas
Zhiqiu Lin
Anas Mahmoud
Bargav Jayaraman
Mark Ibrahim
Melissa Hall
Yunyang Xiong
Jonathan Lebensold
Candace Ross
Srihari Jayakumar
Chuan Guo
Diane Bouchacourt
Haider Al-Tahan
Karthik Padthe … (voir 21 de plus)
Vasu Sharma
Huijuan Xu 0001
Xiaoqing Ellen Tan
Megan Richards
Samuel Lavoie
Pietro Astolfi
Reyhane Askari Hemmat
Jun Chen
Kushal Tirumala
Rim Assouel
Mazda Moayeri
Arjang Talattof
Kamalika Chaudhuri
Zechun Liu
Xilun Chen
Quentin Garrido
Karen Ullrich
Aishwarya Agrawal
Kate Saenko
Asli Celikyilmaz
Vikas Chandra
2024-05-27
ArXiv (prépublication)
doi.org
arxiv.org
Listenable Maps for Zero-Shot Audio Classifiers
Francesco Paissan
Luca Della Libera
Mirco Ravanelli
Cem (Yusuf) Subakan
Interpreting the decisions of deep learning models, including audio classifiers, is crucial for ensuring the transparency and trustworthines… (voir plus)s of this technology. In this paper, we introduce LMAC-ZS (Listenable Maps for Audio Classifiers in the Zero-Shot context), which, to the best of our knowledge, is the first decoder-based post-hoc interpretation method for explaining the decisions of zero-shot audio classifiers. The proposed method utilizes a novel loss function that maximizes the faithfulness to the original similarity between a given text-and-audio pair. We provide an extensive evaluation using the Contrastive Language-Audio Pretraining (CLAP) model to showcase that our interpreter remains faithful to the decisions in a zero-shot classification context. Moreover, we qualitatively show that our method produces meaningful explanations that correlate well with different text prompts.
2024-05-27
ArXiv (prépublication)
doi.org
arxiv.org
Neuro-GPT: Towards A Foundation Model for EEG
Wenhui Cui
Woojae Jeong
Philipp Thölke
Takfarinas Medani
Karim Jerbi
Anand A. Joshi
Richard M. Leahy
To handle the scarcity and heterogeneity of electroencephalography (EEG) data for Brain-Computer Interface (BCI) tasks, and to harness the p… (voir plus)ower of large publicly available data sets, we propose Neuro-GPT, a foundation model consisting of an EEG encoder and a GPT model. The foundation model is pre-trained on a large-scale data set using a self-supervised task that learns how to reconstruct masked EEG segments. We then fine-tune the model on a Motor Imagery Classification task to validate its performance in a low-data regime (9 subjects). Our experiments demonstrate that applying a foundation model can significantly improve classification performance compared to a model trained from scratch, which provides evidence for the generalizability of the foundation model and its ability to address challenges of data scarcity and heterogeneity in EEG. The code is publicly available at github.com/wenhui0206/NeuroGPT.
2024-05-27
2024 IEEE International Symposium on Biomedical Imaging (ISBI) (publié)
doi.org
arxiv.org
Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents
Safa Alver
Ali Rahimi-Kalahroudi
Doina Precup
In neuroscience, one of the key behavioral tests for determining whether a subject of study exhibits model-based behavior is to study its ad… (voir plus)aptiveness to local changes in the environment. In reinforcement learning, however, recent studies have shown that modern model-based agents display poor adaptivity to such changes. The main reason for this is that modern agents are typically designed to improve sample efficiency in single task settings and thus do not take into account the challenges that can arise in other settings. In local adaptation settings, one particularly important challenge is in quickly building and maintaining a sufficiently accurate model after a local change. This is challenging for deep model-based agents as their models and replay buffers are monolithic structures lacking distribution shift handling capabilities. In this study, we show that the conceptually simple idea of partial models can allow deep model-based agents to overcome this challenge and thus allow for building locally adaptive model-based agents. By modeling the different parts of the state space through different models, the agent can not only maintain a model that is accurate across the state space, but it can also quickly adapt it in the presence of a local change in the environment. We demonstrate this by showing that the use of partial models in agents such as deep Dyna-Q, PlaNet and Dreamer can allow for them to effectively adapt to the local changes in their environments.
2024-05-27
ArXiv (prépublication)
doi.org
arxiv.org
WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average
Louis Fournier
Adel Nabli
Masih Aminbeidokhti
Marco Pedersoli
Eugene Belilovsky
Edouard Oyallon
The performance of deep neural networks is enhanced by ensemble methods, which average the output of several models. However, this comes at … (voir plus)an increased cost at inference. Weight averaging methods aim at balancing the generalization of ensembling and the inference speed of a single model by averaging the parameters of an ensemble of models. Yet, naive averaging results in poor performance as models converge to different loss basins, and aligning the models to improve the performance of the average is challenging. Alternatively, inspired by distributed training, methods like DART and PAPA have been proposed to train several models in parallel such that they will end up in the same basin, resulting in good averaging accuracy. However, these methods either compromise ensembling accuracy or demand significant communication between models during training. In this paper, we introduce WASH, a novel distributed method for training model ensembles for weight averaging that achieves state-of-the-art image classification accuracy. WASH maintains models within the same basin by randomly shuffling a small percentage of weights during training, resulting in diverse models and lower communication costs compared to standard parameter averaging methods.
2024-05-27
ArXiv (prépublication)
arxiv.org
arxiv.org
AdaFisher: Adaptive Second Order Optimization via Fisher Information
Damien Martins Gomes
Yanlei Zhang
Eugene Belilovsky
Guy Wolf
Mahdi S. Hosseini
First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limi… (voir plus)ted curvature information by employing the diagonal matrix preconditioning of the stochastic gradient during the training. Despite their widespread, second-order optimization algorithms exhibit superior convergence properties compared to their first-order counterparts e.g. Adam and SGD. However, their practicality in training DNNs are still limited due to increased per-iteration computations and suboptimal accuracy compared to the first order methods. We present AdaFisher--an adaptive second-order optimizer that leverages a block-diagonal approximation to the Fisher information matrix for adaptive gradient preconditioning. AdaFisher aims to bridge the gap between enhanced convergence capabilities and computational efficiency in second-order optimization framework for training DNNs. Despite the slow pace of second-order optimizers, we showcase that AdaFisher can be reliably adopted for image classification, language modelling and stand out for its stability and robustness in hyperparameter tuning. We demonstrate that AdaFisher outperforms the SOTA optimizers in terms of both accuracy and convergence speed. Code available from \href{https://github.com/AtlasAnalyticsLab/AdaFisher}{https://github.com/AtlasAnalyticsLab/AdaFisher}
2024-05-26
ArXiv (prépublication)
doi.org
arxiv.org
Stimulus information guides the emergence of behavior-related signals in primary somatosensory cortex during learning.
Mariangela Panniello
Colleen J Gillon
Roberto Maffulli
Marco Celotto
Stefano Panzeri
Blake Richards
Michael M Kohl
2024-05-25
Cell Reports (publié)
doi.org
Towards a Generic Representation of Combinatorial Problems for Learning-Based Approaches
Léo Boisvert
Hélène Verhaeghe
Quentin Cappart
2024-05-25
Integration of Constraint Programming, Artificial Intelligence, and Operations Research (publié)
doi.org
arxiv.org
Efficient Adversarial Training in LLMs with Continuous Attacks
Sophie Xhonneux
Alessandro Sordoni
Stephan Günnemann
Gauthier Gidel
Leo Schwinn
Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial tra… (voir plus)ining has proven to be one of the most promising methods to reliably improve robustness against such attacks. Yet, in the context of LLMs, current methods for adversarial training are hindered by the high computational costs required to perform discrete adversarial attacks at each training iteration. We address this problem by instead calculating adversarial attacks in the continuous embedding space of the LLM, which is orders of magnitudes more efficient. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses: the first makes the model robust on continuous embedding attacks computed on an adversarial behaviour dataset; the second ensures the usefulness of the final model by fine-tuning on utility data. Moreover, we introduce C-AdvIPO, an adversarial variant of IPO that does not require utility data for adversarially robust alignment. Our empirical evaluation on four models from different families (Gemma, Phi3, Mistral, Zephyr) and at different scales (2B, 3.8B, 7B) shows that both algorithms substantially enhance LLM robustness against discrete attacks (GCG, AutoDAN, PAIR), while maintaining utility. Our results demonstrate that robustness to continuous perturbations can extrapolate to discrete threat models. Thereby, we present a path toward scalable adversarial training algorithms for robustly aligning LLMs.
2024-05-24
ArXiv (prépublication)
doi.org
arxiv.org