Portrait of Eva Portelance

Eva Portelance

Associate Academic Member
Assistant Professor, HEC Montréal, Department of Decision Sciences
IVADOLabs
Research Topics
Cognitive Science
Natural Language Processing
Website
Google Scholar
LinkedIn
X

Biography

I'm an Assistant Professor of Machine Learning in the Department of Decision Sciences at HEC Montréal. I'm also an Associate Academic member at Mila - Quebec Artificial Intelligence Institute.

My research intersects AI and Cognitive Science. I'm interested in studying how both humans and machines learn to understand language and reason about complex problems.

Before joining HEC Montréal, I was a postdoctoral fellow at Mila and McGill University’s NLP Group working with Timothy O’Donnell and Siva Reddy.

I completed my PhD in computational/cognitive linguistics at Stanford University, co-advised by professors Dan Jurafsky and Mike C. Frank, as part of the Stanford NLP group and the Stanford Language and Cognition Lab. I'm an interdisciplinarian at heart with a knack for hard problems.

Current Students

Nicolas Bosteels
Master's Research - Université de Montréal
Github
Nicolas Goulet
PhD - HEC Montréal
Co-supervisor :
Laurent Charlin
Google Scholar

Publications

Publisher Correction: On the compatibility of generative AI and generative linguistics
Eva Portelance
Masoud Jasbi
2025-11-23
Nature Computational Science (published)
doi.org
"On the goals of linguistic theory": Revisiting Chomskyan theories in the era of AI
Eva Portelance
Masoud Jasbi
Theoretical linguistics seeks to explain what human language is, and why. Linguists and cognitive scientists have proposed different theoret… (see more)ical models of what language is, as well as cognitive factors that shape it, and allow humans to 'produce', 'understand', and 'acquire' natural languages. However, humans may no longer be the only ones learning to 'generate', 'parse', and 'learn' natural language: artificial intelligence (AI) models such as large language models are proving to have impressive linguistic capabilities. Many are thus questioning what role, if any, such models should play in helping theoretical linguistics reach its ultimate research goals? In this paper, we propose to answer this question, by reiterating the tenets of generative linguistics, a leading school of thought in the field, and by considering how AI models as theories of language relate to each of these important concepts. Specifically, we consider three foundational principles, finding roots in the early works of Noam Chomsky: (1) levels of theoretical adequacy; (2) procedures for linguistic theory development; (3) language learnability and Universal Grammar. In our discussions of each principle, we give special attention to two types of AI models: neural language models and neural grammar induction models. We will argue that such models, in particular neural grammar induction models, do have a role to play, but that this role is largely modulated by the stance one takes regarding each of these three guiding principles.
2024-12-31
Nat. Comput. Sci. (published)
doi.org
arxiv.org
The roles of neural networks in language acquisition
Eva Portelance
Masoud Jasbi

How can modern neural networks like large language models be useful to the field of language acquisition, and more broadly cognitive scie… (see more)nce, if they are not a priori designed to be cognitive models? As developments towards natural language understanding and generation have improved leaps and bounds, with models like GPT-4, the question of how they can inform our understanding of human language acquisition has re-emerged. As such, it is critical to examine how in practice linking hypotheses between models and human learners can be safely established. To address these questions, we propose a model taxonomy, including four modeling approaches, each having differing goals, from exploratory hypothesis generation to hypothesis differentiation and testing. We show how the goals of these approaches align with the overarching goals of science and linguistics by connecting our taxonomy to the realist vs. instrumentalist approaches in philosophy of science. We survey recent work having adopted each of our modelling approaches and address the importance of computational modelling in language acquisition studies.

2024-10-23
Language and Linguistics Compass (published)
doi.org
VinePPO: Accurate Credit Assignment in RL for LLM Mathematical Reasoning
Amirhossein Kazemnejad
Milad Aghajohari
Eva Portelance
Alessandro Sordoni
Siva Reddy
Aaron Courville
Nicolas Roux
Large language models (LLMs) are increasingly required to solve complex reasoning tasks, like mathematical problems, that involve multiple r… (see more)easoning steps before feedback is received. Effectively identifying and prioritizing key steps by accurately assigning credit to these intermediate steps is essential for enhancing model performance. Proximal Policy Optimization (PPO), a state-of-the-art reinforcement learning algorithm for finetuning LLMs, addresses the credit assignment problem by employing value networks to predict the expected cumulative rewards of intermediate states. In this work, we identify significant limitations with this value estimation method. To address this, we propose \methodname that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates of the intermediate values. VinePPO consistently outperforms standard PPO, doing so more efficiently and with lower divergence from the reference model. Our findings underscore the critical importance of accurate credit assignment in LLM post-training and present a simple, yet effective solution.
2024-10-08
NeurIPS.cc/2024/Workshop/MATH-AI (accepted)
openreview.net
openreview.net
VinePPO: Refining Credit Assignment in RL Training of LLMs
Amirhossein Kazemnejad
Milad Aghajohari
Eva Portelance
Alessandro Sordoni
Siva Reddy
Aaron Courville
Nicolas Le Roux
Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receivi… (see more)ng any reward. Properly assigning credit to these steps is essential for enhancing model performance. Proximal Policy Optimization (PPO), a common reinforcement learning (RL) algorithm used for LLM finetuning, employs value networks to tackle credit assignment. However, recent approaches achieve strong results without it, raising questions about the efficacy of value networks in practice. In this work, we systematically evaluate the efficacy of value networks and reveal their significant shortcomings in reasoning-heavy LLM tasks, showing that they often produce poor estimate of expected return and barely outperform a random baseline when comparing alternative steps. This motivates our key question: Can improved credit assignment enhance RL training for LLMs? To address this, we propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates. Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time (up to 3.0x). Crucially, it achieves higher test accuracy for a given training accuracy, capturing more generalization signal per sample. These results emphasize the importance of accurate credit assignment in RL training of LLM.
2024-10-01
arXiv (preprint)
doi.org
proceedings.mlr.press
Learning Action and Reasoning-Centric Image Editing from Videos and Simulation
Benno Krojer
Dheeraj Vattikonda
Luis Lara
Varun Jampani
Eva Portelance
Christopher Pal
Siva Reddy
2024-09-25
NeurIPS.cc/2024/Datasets_and_Benchmarks_Track (spotlight)
openreview.net
openreview.net
Learning Action and Reasoning-Centric Image Editing from Videos and Simulations
Benno Krojer
Dheeraj Vattikonda
Luis Lara
Varun Jampani
Eva Portelance
Christopher Pal
Siva Reddy
2024-07-02
arXiv (preprint)
doi.org
arxiv.org
Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models
Eva Portelance
Siva Reddy
Timothy J. O'Donnell
Semantic and syntactic bootstrapping posit that children use their prior knowledge of one linguistic domain, say syntactic relations, to hel… (see more)p later acquire another, such as the meanings of new words. Empirical results supporting both theories may tempt us to believe that these are different learning strategies, where one may precede the other. Here, we argue that they are instead both contingent on a more general learning strategy for language acquisition: joint learning. Using a series of neural visually-grounded grammar induction models, we demonstrate that both syntactic and semantic bootstrapping effects are strongest when syntax and semantics are learnt simultaneously. Joint learning results in better grammar induction, realistic lexical category learning, and better interpretations of novel sentence and verb meanings. Joint learning makes language acquisition easier for learners by mutually constraining the hypotheses spaces for both syntax and semantics. Studying the dynamics of joint inference over many input sources and modalities represents an important new direction for language modeling and learning research in both cognitive sciences and AI, as it may help us explain how language can be acquired in more constrained learning settings.
2023-12-31
arXiv (preprint)
doi.org
arxiv.org