Le traitement du langage naturel à l'ère de l'IA générative
Rejoignez-nous à Mila en octobre pour un atelier de trois jour visant à explorer le potentiel de transformation des technologies langagières et leurs implications pour la société.
Ce programme est conçu pour fournir aux professionnel·le·s travaillant dans le domaine de la politique une compréhension fondamentale de la technologie de l'IA.
Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
Publications
Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi
Cooperative Multi-agent Reinforcement Learning (MARL) algorithms with Zero-Shot Coordination (ZSC) have gained significant attention in rece… (voir plus)nt years. ZSC refers to the ability of agents to coordinate zero-shot (without additional interaction experience) with independently trained agents. While ZSC is crucial for cooperative MARL agents, it might not be possible for complex tasks and changing environments. Agents also need to adapt and improve their performance with minimal interaction with other agents. In this work, we show empirically that state-of-the-art ZSC algorithms have poor performance when paired with agents trained with different learning methods, and they require millions of interaction samples to adapt to these new partners. To investigate this issue, we formally defined a framework based on a popular cooperative multi-agent game called Hanabi to evaluate the adaptability of MARL methods. In particular, we created a diverse set of pre-trained agents and defined a new metric called adaptation regret that measures the agent's ability to efficiently adapt and improve its coordination performance when paired with some held-out pool of partners on top of its ZSC performance. After evaluating several SOTA algorithms using our framework, our experiments reveal that naive Independent Q-Learning (IQL) agents in most cases adapt as quickly as the SOTA ZSC algorithm Off-Belief Learning (OBL). This finding raises an interesting research question: How to design MARL algorithms with high ZSC performance and capability of fast adaptation to unseen partners. As a first step, we studied the role of different hyper-parameters and design choices on the adaptability of current MARL algorithms. Our experiments show that two categories of hyper-parameters controlling the training data diversity and optimization process have a significant impact on the adaptability of Hanabi agents.
Recent advancements in large language models have demonstrated remarkable capabilities across various NLP tasks. But many questions remain, … (voir plus)including whether open-source models match closed ones, why these models excel or struggle with certain tasks, and what types of practical procedures can improve performance. We address these questions in the context of classification by evaluating three classes of models using eight datasets across three distinct tasks: named entity recognition, political party prediction, and misinformation detection. While larger LLMs often lead to improved performance, open-source models can rival their closed-source counterparts by fine-tuning. Moreover, supervised smaller models, like RoBERTa, can achieve similar or even greater performance in many datasets compared to generative LLMs. On the other hand, closed models maintain an advantage in hard tasks that demand the most generalizability. This study underscores the importance of model selection based on task requirements
In this paper, we create YORC: a new multi-choice Yoruba Reading Comprehension dataset that is based on Yoruba high-school reading comprehen… (voir plus)sion examination. We provide baseline results by performing cross-lingual transfer using existing English RACE dataset based on a pre-trained encoder-only model. Additionally, we provide results by prompting large language models (LLMs) like GPT-4.
We use the Galaxy Morphology Posterior Estimation Network (GaMPEN) to estimate morphological parameters and associated uncertainties for ∼… (voir plus)8 million galaxies in the Hyper Suprime-Cam Wide survey with z ≤ 0.75 and m ≤ 23. GaMPEN is a machine-learning framework that estimates Bayesian posteriors for a galaxy’s bulge-to-total light ratio (L B /L T ), effective radius (R e ), and flux (F). By first training on simulations of galaxies and then applying transfer learning using real data, we trained GaMPEN with 1% of our data set. This two-step process will be critical for applying machine-learning algorithms to future large imaging surveys, such a
Background: During the first year of the COVID-19 pandemic, the proportion of reported cases of COVID-19 among Canadians was under 6%. Altho… (voir plus)ugh high vaccine coverage was achieved in Canada by fall 2021, the Omicron variant caused unprecedented numbers of infections, overwhelming testing capacity and making it difficult to quantify the trajectory of population immunity. Methods: Using a time-series approach and data from more than 900 000 samples collected by 7 research studies collaborating with the COVID-19 Immunity Task Force (CITF), we estimated trends in SARS-CoV-2 seroprevalence owing to infection and vaccination for the Canadian population over 3 intervals: prevaccination (March to November 2020), vaccine roll-out (December 2020 to November 2021), and the arrival of the Omicron variant (December 2021 to March 2023). We also estimated seroprevalence by geographical region and age. Results: By November 2021, 9.0% (95% credible interval [CrI] 7.3%–11%) of people in Canada had humoral immunity to SARS-CoV-2 from an infection. Seroprevalence increased rapidly after the arrival of the Omicron variant — by Mar. 15, 2023, 76% (95% CrI 74%–79%) of the population had detectable antibodies from infections. The rapid rise in infection-induced antibodies occurred across Canada and was most pronounced in younger age groups and in the Western provinces: Manitoba, Saskatchewan, Alberta and British Columbia. Interpretation: Data up to March 2023 indicate that most people in Canada had acquired antibodies against SARS-CoV-2 through natural infection and vaccination. However, given variations in population seropositivity by age and geography, the potential for waning antibody levels, and new variants that may escape immunity, public health policy and clinical decisions should be tailored to local patterns of population immunity.