Portrait of Jonathan Colaço Carr is unavailable

Jonathan Colaço Carr

Master's Research - McGill University
Supervisor
Prakash Panangaden
Co-supervisor
Doina Precup
Research Topics
Machine Learning Theory
Natural Language Processing
Reinforcement Learning

Publications

Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
Khaoula Chehbouni
Jonathan Colaço Carr
Yash More
Jackie CK Cheung
Golnoosh Farnadi
In an effort to mitigate the harms of large language models (LLMs), learning from human feedback (LHF) has been used to steer LLMs towards o… (see more)utputs that are intended to be both less harmful and more helpful. Despite the widespread adoption of LHF in practice, the quality of this feedback and its effectiveness as a safety mitigation technique remain unclear. This study addresses these issues by auditing the widely-used Helpful and Harmless (HH) dataset by Anthropic. Our work includes: (1) a thorough investigation of the dataset's content through both manual and automated evaluation; (2) experiments demonstrating the dataset's impact on models' safety; and (3) an analysis of the 100 most influential papers citing this dataset. Through our audit, we showcase how conceptualization failures and quality issues identified in the HH dataset can create additional harms by leading to disparate safety behaviors across demographic groups. Our findings highlight the need for more nuanced, context-sensitive approaches to safety mitigation in LLMs.
2024-11-11
ArXiv (preprint)
doi.org
arxiv.org
Conditions on Preference Relations that Guarantee the Existence of Optimal Policies
Jonathan Colaço Carr
Prakash Panangaden
Doina Precup
Learning from Preferential Feedback (LfPF) plays an essential role in training Large Language Models, as well as certain types of interactiv… (see more)e learning agents. However, a substantial gap exists between the theory and application of LfPF algorithms. Current results guaranteeing the existence of optimal policies in LfPF problems assume that both the preferences and transition dynamics are determined by a Markov Decision Process. We introduce the Direct Preference Process, a new framework for analyzing LfPF problems in partially-observable, non-Markovian environments. Within this framework, we establish conditions that guarantee the existence of optimal policies by considering the ordinal structure of the preferences. We show that a decision-making problem can have optimal policies -- that are characterized by recursive optimality equations -- even when no reward function can express the learning goal. These findings underline the need to explore preference-based learning strategies which do not assume that preferences are generated by reward.
2024-04-17
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)
doi.org
proceedings.mlr.press