Portrait of Chris Pal

Chris Pal

Core Academic Member
christopher.pal@mila.quebec
Canada CIFAR AI Chair
Full Professor, Polytechnique Montréal, Department of Computer Engineering and Software Engineering
Assistant Professor, Université de Montréal, Department of Computer Science and Operations Research
Research Topics
Deep Learning
Website
Google Scholar
X

Biography

Christopher Pal is a Canada CIFAR AI Chair, full professor at Polytechnique Montréal and adjunct professor in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal. He is also a Distinguished Scientist at ServiceNow Research.

Pal has been involved in AI and machine learning research for over twenty-five years and has published extensively on large-scale language modelling methods and generative modelling techniques. He has a PhD in computer science from the University of Waterloo.

Current Students

Mai Ababneh
Research Intern - McGill University
ababneh.mai@gmail.com
Shubham Agarwal
Postdoctorate - HEC Montréal
Principal supervisor :
Laurent Charlin
Website
Github
Google Scholar
Paul Barde
Collaborating researcher - McGill University
Principal supervisor :
Derek Nowrouzezahrai
paul.b.barde@gmail.com
Website
Github
Google Scholar
Hugo Baudchon
Master's Research - Université de Montréal
Github
Chris Beckham
PhD - Polytechnique Montréal
Can (Sam) Chen
PhD - McGill University
Principal supervisor :
Xue (Steve) Liu
chencan421@gmail.com
Website
Léa Demeule
PhD - Université de Montréal
Principal supervisor :
Glen Berseth
Website
Github
Amine El-hattami
PhD - Polytechnique Montréal
Chris Emezue
Master's Research - Université de Montréal
Co-supervisor :
Derek Nowrouzezahrai
Website
Github
Google Scholar
Matthew Fortier
Collaborating Alumni - Polytechnique Montréal
Github
Google Scholar
Roger Girgis
PhD - Polytechnique Montréal
Florian Golemo
Postdoctorate - McGill University
Co-supervisor :
Gauthier Gidel
fgolemo@gmail.com
Website
Github
Google Scholar
Anthony Gosselin
Master's Research - Polytechnique Montréal
Website
Github
Google Scholar
Simon Guiroy
PhD - Université de Montréal
Co-supervisor :
Sarath Chandar
Website
Github
Google Scholar
Yousef Kotp
Master's Research - Concordia University
Co-supervisor :
Mahdi Hosseini
Website
Github
Google Scholar
Jae Hyun Lim
Collaborating researcher - Université de Montréal
Website
Github
Google Scholar
Michelle Lin
Master's Research - Université de Montréal
Website
Github
Google Scholar
Olga Luo
PhD - Université de Montréal
Joel Moniz
PhD - Polytechnique Montréal
Jonathan Pilault
PhD - Polytechnique Montréal
Github
Google Scholar
Juan Rodriguez
PhD - École de technologie suprérieure
Website
Github
Google Scholar
Luke Rowe
PhD - Université de Montréal
Principal supervisor :
Liam Paull
Website
Github
Google Scholar
Gaurav Sahu
Postdoctorate - HEC Montréal
Principal supervisor :
Laurent Charlin
Website
Github
Google Scholar
Aditya Sharma
PhD - Polytechnique Montréal
Principal supervisor :
Amal Zouaq
Website
Github
Google Scholar
Mattie Tesfaldet
PhD - McGill University
Principal supervisor :
Derek Nowrouzezahrai
Website
Github
Google Scholar
Martin Weiss
PhD - Polytechnique Montréal
Website
Github
Google Scholar

Publications

Language Models Can Reduce Asymmetry in Information Markets
Nasim Rahaman
Martin Weiss
Manuel Wüthrich
Yoshua Bengio
Erran L. Li
Chris Pal
Bernhard Schölkopf
This work addresses the buyer's inspection paradox for information markets. The paradox is that buyers need to access information to determi… (see more)ne its value, while sellers need to limit access to prevent theft. To study this, we introduce an open-source simulated digital marketplace where intelligent agents, powered by language models, buy and sell information on behalf of external participants. The central mechanism enabling this marketplace is the agents' dual capabilities: they not only have the capacity to assess the quality of privileged information but also come equipped with the ability to forget. This ability to induce amnesia allows vendors to grant temporary access to proprietary information, significantly reducing the risk of unauthorized retention while enabling agents to accurately gauge the information's relevance to specific queries or tasks. To perform well, agents must make rational decisions, strategically explore the marketplace through generated sub-queries, and synthesize answers from purchased information. Concretely, our experiments (a) uncover biases in language models leading to irrational behavior and evaluate techniques to mitigate these biases, (b) investigate how price affects demand in the context of informational goods, and (c) show that inspection and higher budgets both lead to higher quality outcomes.
2024-03-21
ArXiv (preprint)
doi.org
arxiv.org
Language Models Can Reduce Asymmetry in Information Markets
Nasim Rahaman
Martin Weiss
Manuel Wüthrich
Yoshua Bengio
Erran L. Li
Chris Pal
Bernhard Schölkopf
2024-03-21
ArXiv (preprint)
doi.org
arxiv.org
Multi-Resolution Continuous Normalizing Flows
Vikram Voleti
Chris Finlay
Adam M. Oberman
Chris Pal
2024-03-21
Annals of Mathematics and Artificial Intelligence (published)
doi.org
openreview.net
IntentGPT: Few-shot Intent Discovery with Large Language Models
Juan A. Rodriguez
Nicholas Botzer
David Vazquez
Chris Pal
Marco Pedersoli
Issam Hadj Laradji
2024-03-11
ICLR.cc/2024/Workshop/LLMAgents (poster)
openreview.net
openreview.net
IntentGPT: Few-shot Intent Discovery with Large Language Models
Juan A. Rodriguez
Nicholas Botzer
David Vazquez
Chris Pal
Marco Pedersoli
Issam Hadj Laradji
2024-03-11
ICLR.cc/2024/Workshop/LLMAgents (poster)
doi.org
openreview.net
Self-evaluation and self-prompting to improve the reliability of LLMs
Alexandre Piché
Aristides Milios
Dzmitry Bahdanau
Chris Pal
In order to safely deploy Large Language Models (LLMs), they must be capable of dynamically adapting their behavior based on their level of … (see more)knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to as self-restraint, is non-trivial to teach since it depends on the internal knowledge of an LLM. By default, LLMs are trained to maximize the next token likelihood which does not teach the model to modulate its answer based on its level of uncertainty. In order to learn self-restraint, we devise a simple objective that can encourage the model to produce generation that the model is confident in. To optimize this objective, we introduce ReSearch, an iterative search algorithm based on self-evaluation and self-prompting. Our method results in fewer hallucinations overall, both for known and unknown topics, as the model learns to selectively restrain itself. In addition, our method elegantly incorporates the ability to decline, when the model assesses that it cannot provide a response without a high proportion of hallucination.
2024-03-04
ICLR.cc/2024/Workshop/SeT_LLM (published)
openreview.net
openreview.net
Self-evaluation and self-prompting to improve the reliability of LLMs
Alexandre Piché
Aristides Milios
Dzmitry Bahdanau
Chris Pal
In order to safely deploy Large Language Models (LLMs), they must be capable of dynamically adapting their behavior based on their level of … (see more)knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to as self-restraint, is non-trivial to teach since it depends on the internal knowledge of an LLM. By default, LLMs are trained to maximize the next token likelihood which does not teach the model to modulate its answer based on its level of uncertainty. In order to learn self-restraint, we devise a simple objective that can encourage the model to produce generation that the model is confident in. To optimize this objective, we introduce ReSearch, an iterative search algorithm based on self-evaluation and self-prompting. Our method results in fewer hallucinations overall, both for known and unknown topics, as the model learns to selectively restrain itself. In addition, our method elegantly incorporates the ability to decline, when the model assesses that it cannot provide a response without a high proportion of hallucination.
2024-03-04
ICLR.cc/2024/Workshop/SeT_LLM (published)
openreview.net
openreview.net
Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots
Simon Chamorro
Victor Klemm
Miguel de La Iglesia Valls
Chris Pal
Roland Siegwart
In recent years, legged and wheeled-legged robots have gained prominence for tasks in environments predominantly created for humans across v… (see more)arious domains. One significant challenge faced by many of these robots is their limited capability to navigate stairs, which hampers their functionality in multi-story environments. This study proposes a method aimed at addressing this limitation, employing reinforcement learning to develop a versatile controller applicable to a wide range of robots. In contrast to the conventional velocity-based controllers, our approach builds upon a position-based formulation of the RL task, which we show to be vital for stair climbing. Furthermore, the methodology leverages an asymmetric actor-critic structure, enabling the utilization of privileged information from simulated environments during training while eliminating the reliance on exteroceptive sensors during real-world deployment. Another key feature of the proposed approach is the incorporation of a boolean observation within the controller, enabling the activation or deactivation of a stair-climbing mode. We present our results on different quadrupeds and bipedal robots in simulation and showcase how our method allows the balancing robot Ascento to climb 15cm stairs in the real world, a task that was previously impossible for this robot.
2024-02-09
ArXiv (preprint)
doi.org
arxiv.org
Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots
Simon Chamorro
Victor Klemm
Miguel de La Iglesia Valls
Chris Pal
Roland Siegwart
In recent years, legged and wheeled-legged robots have gained prominence for tasks in environments predominantly created for humans across v… (see more)arious domains. One significant challenge faced by many of these robots is their limited capability to navigate stairs, which hampers their functionality in multi-story environments. This study proposes a method aimed at addressing this limitation, employing reinforcement learning to develop a versatile controller applicable to a wide range of robots. In contrast to the conventional velocity-based controllers, our approach builds upon a position-based formulation of the RL task, which we show to be vital for stair climbing. Furthermore, the methodology leverages an asymmetric actor-critic structure, enabling the utilization of privileged information from simulated environments during training while eliminating the reliance on exteroceptive sensors during real-world deployment. Another key feature of the proposed approach is the incorporation of a boolean observation within the controller, enabling the activation or deactivation of a stair-climbing mode. We present our results on different quadrupeds and bipedal robots in simulation and showcase how our method allows the balancing robot Ascento to climb 15cm stairs in the real world, a task that was previously impossible for this robot.
2024-02-09
ArXiv (preprint)
doi.org
arxiv.org
LitLLM: A Toolkit for Scientific Literature Review
Shubham Agarwal
Issam Hadj Laradji
Laurent Charlin
Chris Pal
Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work.… (see more) It is a tedious task which makes an automatic literature review generator appealing. Unfortunately, many existing works that generate such reviews using Large Language Models (LLMs) have significant limitations. They tend to hallucinate-generate non-actual information-and ignore the latest research they have not been trained on. To address these limitations, we propose a toolkit that operates on Retrieval Augmented Generation (RAG) principles, specialized prompting and instructing techniques with the help of LLMs. Our system first initiates a web search to retrieve relevant papers by summarizing user-provided abstracts into keywords using an off-the-shelf LLM. Authors can enhance the search by supplementing it with relevant papers or keywords, contributing to a tailored retrieval process. Second, the system re-ranks the retrieved papers based on the user-provided abstract. Finally, the related work section is generated based on the re-ranked results and the abstract. There is a substantial reduction in time and effort for literature review compared to traditional methods, establishing our toolkit as an efficient alternative. Our open-source toolkit is accessible at https://github.com/shubhamagarwal92/LitLLM and Huggingface space (https://huggingface.co/spaces/shubhamagarwal92/LitLLM) with the video demo at https://youtu.be/E2ggOZBAFw0.
2024-02-02
ArXiv (preprint)
doi.org
arxiv.org
LitLLM: A Toolkit for Scientific Literature Review
Shubham Agarwal
Issam Hadj Laradji
Laurent Charlin
Chris Pal
Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work.… (see more) It is a tedious task which makes an automatic literature review generator appealing. Unfortunately, many existing works that generate such reviews using Large Language Models (LLMs) have significant limitations. They tend to hallucinate-generate non-actual information-and ignore the latest research they have not been trained on. To address these limitations, we propose a toolkit that operates on Retrieval Augmented Generation (RAG) principles, specialized prompting and instructing techniques with the help of LLMs. Our system first initiates a web search to retrieve relevant papers by summarizing user-provided abstracts into keywords using an off-the-shelf LLM. Authors can enhance the search by supplementing it with relevant papers or keywords, contributing to a tailored retrieval process. Second, the system re-ranks the retrieved papers based on the user-provided abstract. Finally, the related work section is generated based on the re-ranked results and the abstract. There is a substantial reduction in time and effort for literature review compared to traditional methods, establishing our toolkit as an efficient alternative. Our open-source toolkit is accessible at https://github.com/shubhamagarwal92/LitLLM and Huggingface space (https://huggingface.co/spaces/shubhamagarwal92/LitLLM) with the video demo at https://youtu.be/E2ggOZBAFw0.
2024-02-02
ArXiv (preprint)
doi.org
arxiv.org
LitLLM: A Toolkit for Scientific Literature Review
Shubham Agarwal
Issam Hadj Laradji
Laurent Charlin
Chris Pal
Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work.… (see more) It is a tedious task which makes an automatic literature review generator appealing. Unfortunately, many existing works that generate such reviews using Large Language Models (LLMs) have significant limitations. They tend to hallucinate-generate non-actual information-and ignore the latest research they have not been trained on. To address these limitations, we propose a toolkit that operates on Retrieval Augmented Generation (RAG) principles, specialized prompting and instructing techniques with the help of LLMs. Our system first initiates a web search to retrieve relevant papers by summarizing user-provided abstracts into keywords using an off-the-shelf LLM. Authors can enhance the search by supplementing it with relevant papers or keywords, contributing to a tailored retrieval process. Second, the system re-ranks the retrieved papers based on the user-provided abstract. Finally, the related work section is generated based on the re-ranked results and the abstract. There is a substantial reduction in time and effort for literature review compared to traditional methods, establishing our toolkit as an efficient alternative. Our open-source toolkit is accessible at https://github.com/shubhamagarwal92/LitLLM and Huggingface space (https://huggingface.co/spaces/shubhamagarwal92/LitLLM) with the video demo at https://youtu.be/E2ggOZBAFw0.
2024-02-02
ArXiv (preprint)
doi.org
arxiv.org