Publications

Enhancing Supervised Visualization Through Autoencoder and Random Forest Proximities for Out-of-Sample Extension
Shuang Ni
Adrien Aumon
Guy Wolf
Kevin R. Moon
Jake S. Rhodes
The value of supervised dimensionality reduction lies in its ability to uncover meaningful connections between data features and labels. Com… (voir plus)mon dimensionality reduction methods embed a set of fixed, latent points, but are not capable of generalizing to an unseen test set. In this paper, we provide an out-of-sample extension method for the random forest-based supervised dimensionality reduction method, RF-PHATE, combining information learned from the random forest model with the function-learning capabilities of autoencoders. Through quantitative assessment of various autoencoder architectures, we identify that networks that reconstruct random forest proximities are more robust for the embedding extension problem. Furthermore, by leveraging proximity-based prototypes, we achieve a 40% reduction in training time without compromising extension quality. Our method does not require label information for out-of-sample points, thus serving as a semi-supervised method, and can achieve consistent quality using only 10% of the training data.
2023-12-31
MLSP (publié)
doi.org
arxiv.org
Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering
Vaibhav Adlakha
Parishad BehnamGhader
Xing Han Lu
Nicholas Meade
Siva Reddy
Retriever-augmented instruction-following models are attractive alternatives to fine-tuned approaches for information-seeking tasks such as … (voir plus)question answering (QA). By simply prepending retrieved documents in its input along with an instruction, these models can be adapted to various information domains and tasks without additional fine-tuning. While the model responses tend to be natural and fluent, the additional verbosity makes traditional QA evaluation metrics such as exact match (EM) and F1 unreliable for accurately quantifying model performance. In this work, we investigate the performance of instruction-following models across three information-seeking QA tasks. We use both automatic and human evaluation to evaluate these models along two dimensions: 1) how well they satisfy the user's information need (correctness), and 2) whether they produce a response based on the provided knowledge (faithfulness). Guided by human evaluation and analysis, we highlight the shortcomings of traditional metrics for both correctness and faithfulness. We then propose simple token-overlap based and model-based metrics that reflect the true performance of these models. Our analysis reveals that instruction-following models are competitive, and sometimes even outperform fine-tuned models for correctness. However, these models struggle to stick to the provided knowledge and often hallucinate in their responses. We hope our work encourages a more holistic evaluation of instruction-following models for QA. Our code and data is available at https://github.com/McGill-NLP/instruct-qa
2023-12-31
Transactions of the Association for Computational Linguistics (publié)
doi.org
arxiv.org
Evaluating Supervision Levels Trade-Offs for Infrared-Based People Counting
David Latortue
Moetez Kdayem
Fidel A. Guerrero Peña
Eric Granger
Marco Pedersoli
Object detection models are commonly used for people counting (and localization) in many applications but require a dataset with costly boun… (voir plus)ding box annotations for training. Given the importance of privacy in people counting, these models rely more and more on infrared images, making the task even harder. In this paper, we explore how weaker levels of supervision affect the performance of deep person counting architectures for image classification and point-level localization. Our experiments indicate that counting people using a convolutional neural network with image-level annotation achieves a level of accuracy that is competitive with YOLO detectors and point-level localization models yet provides a higher frame rate and a simi-lar amount of model parameters. Our code is available at: https://github.com/tortueTortue/IRPeopleCounting.
2023-12-31
2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) (publié)
doi.org
arxiv.org
Evaluating WMT 2024 Metrics Shared Task Submissions on AfriMTE (the African Challenge Set)
Jiayi Wang
David Ifeoluwa Adelani
Pontus Stenetorp
2023-12-31
Conference on Machine Translation (publié)
doi.org
Evaluation algorithmique inclusive de la qualité des espaces publics
Shin Koseki
Toumadher Ammar
Rashid Ahmad Mushkani
Hugo Berard
Sarah Tannir
2023-12-31
SHS Web of Conferences (publié)
doi.org
An Evaluation of Language Models for Hyperpartisan Ideology Detection in Persian Twitter
Sahar Omidi Shayegan
Isar Nejadgholi
Kellin Pelrine
Hao Yu
Sacha Lévy
Zachary Yang
Jean-François Godbout
Reihaneh Rabbany
Large Language Models (LLMs) have shown significant promise in various tasks, including identifying the political beliefs of English-speakin… (voir plus)g social media users from their posts. However, assessing LLMs for this task in non-English languages remains unexplored. In this work, we ask to what extent LLMs can predict the political ideologies of users in Persian social media. To answer this question, we first acknowledge that political parties are not well-defined among Persian users, and therefore, we simplify the task to a much simpler task of hyperpartisan ideology detection. We create a new benchmark and show the potential and limitations of both open-source and commercial LLMs in classifying the hyper-partisan ideologies of users. We compare these models with smaller fine-tuned models, both on the Persian language (ParsBERT) and translated data (RoBERTa), showing that they considerably outperform generative LLMs in this task. We further demonstrate that the performance of the generative LLMs degrades when classifying users based on their tweets instead of their bios and even when tweets are added as additional information, whereas the smaller fine-tuned models are robust and achieve similar performance for all classes. This study is a first step toward political ideology detection in Persian Twitter, with implications for future research to understand the dynamics of ideologies in Persian social media.
2023-12-31
EURALI (publié)
www.semanticscholar.org
An Exact Method for (Constrained) Assortment Optimization Problems with Product Costs
Markus Leitner
Andrea Lodi
Roberto Roberti
Claudio Sole
2023-12-31
INFORMS J. Comput. (publié)
doi.org
arxiv.org
An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics
Saba Ahmadi
Aishwarya Agrawal
2023-12-31
EACL (Findings) (publié)
doi.org
arxiv.org
Exploratory Study on the Impact of English Bias of Generative Large Language Models in Dutch and French
Ayla Rigouts Terryn
Miryam de Lhoneux
2023-12-31
HUMEVAL (publié)
www.semanticscholar.org
Exploring Quantization for Efficient Pre-Training of Transformer Language Models
Kamran Chitsaz
Quentin Fournier
Goncalo Mordido
A. Chandar
The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has p… (voir plus)roven to be effective after pre-training and during fine-tuning, applying quantization in Transformers during pre-training has remained largely unexplored at scale for language modeling. This study aims to explore the impact of quantization for efficient pre-training of Transformers, with a focus on linear layer components. By systematically applying straightforward linear quantization to weights, activations, gradients, and optimizer states, we assess its effects on model efficiency, stability, and performance during training. By offering a comprehensive recipe of effective quantization strategies to be applied during the pre-training of Transformers, we promote high training efficiency from scratch while retaining language modeling ability. Code is available at https://github.com/chandar-lab/EfficientLLMs.
2023-12-31
EMNLP (Findings) (publié)
doi.org
arxiv.org
Fairness Through Domain Awareness: Mitigating Popularity Bias For Music Discovery
Rebecca Salganik
Fernando Diaz
Golnoosh Farnadi
As online music platforms grow, music recommender systems play a vital role in helping users navigate and discover content within their vast… (voir plus) musical databases. At odds with this larger goal, is the presence of popularity bias, which causes algorithmic systems to favor mainstream content over, potentially more relevant, but niche items. In this work we explore the intrinsic relationship between music discovery and popularity bias. To mitigate this issue we propose a domain-aware, individual fairness-based approach which addresses popularity bias in graph neural network (GNNs) based recommender systems. Our approach uses individual fairness to reflect a ground truth listening experience, i.e., if two songs sound similar, this similarity should be reflected in their representations. In doing so, we facilitate meaningful music discovery that is robust to popularity bias and grounded in the music domain. We apply our BOOST methodology to two discovery based tasks, performing recommendations at both the playlist level and user level. Then, we ground our evaluation in the cold start setting, showing that our approach outperforms existing fairness benchmarks in both performance and recommendation of lesser-known content. Finally, our analysis explains why our proposed methodology is a novel and promising approach to mitigating popularity bias and improving the discovery of new and niche content in music recommender systems.
2023-12-31
ECIR (4) (publié)
doi.org
arxiv.org
Fairness Under Demographic Scarce Regime
Patrik Joslin Kenfack
S Ebrahimi Kahou
Ulrich Matchi Aïvodji
Most existing works on fairness assume the model has full access to demographic information. However, there exist scenarios where demographi… (voir plus)c information is partially available because a record was not maintained throughout data collection or due to privacy reasons. This setting is known as demographic scarce regime. Prior research have shown that training an attribute classifier to replace the missing sensitive attributes (proxy) can still improve fairness. However, the use of proxy-sensitive attributes worsens fairness-accuracy trade-offs compared to true sensitive attributes. To address this limitation, we propose a framework to build attribute classifiers that achieve better fairness-accuracy trade-offs. Our method introduces uncertainty awareness in the attribute classifier and enforces fairness on samples with demographic information inferred with the lowest uncertainty. We show empirically that enforcing fairness constraints on samples with uncertain sensitive attributes is detrimental to fairness and accuracy. Our experiments on two datasets showed that the proposed framework yields models with significantly better fairness-accuracy trade-offs compared to classic attribute classifiers. Surprisingly, our framework outperforms models trained with constraints on the true sensitive attributes.
2023-12-31
Trans. Mach. Learn. Res. (publié)
doi.org
openreview.net