Skip To Main Content
Barry-John Theobald on Muck Rack

Barry-John Theobald

As seen in: arXiv
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile

Get in touch with Barry-John

Contact Barry-John, search articles and posts on X, monitor coverage, and track replies from one place.

Learn more about Muck Rack

Actions

Share this page

Is this you?

As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile

Articles

Computer Science > Machine Learning

|
By Lucas Monteiro Verified, Natalie Mackraz, Barry-John Theobald
| arXiv
[Submitted on 8 May 2026] Title:Theoretical Limits of Language Model Alignment View a PDF of the paper titled Theoretical Limits of Language Model Alignment, by Lucas Monteiro Paes and Natalie Mackraz and Barry-John Theobald and Federico Danieli View PDF HTML (experimental) Abstract:Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model.
Open in Who Shared Issue with article?

PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectories

|
By Barry-John Theobald, Katherine Metcalf, Natalie Mackraz
| arXiv
[Submitted on 8 Oct 2024] Title:PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectories View a PDF of the paper titled PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectories, by Stephane Aroca-Ouellette and 3 other authors View PDF HTML (experimental) Abstract:Accommodating human preferences is essential for creating AI agents that deliver personalized and effective interactions.
Open in Who Shared Issue with article?

[2211.06527] Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning

|
By Barry-John Theobald, Miguel Sarabia
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (693) Issue with article?
See all 4 articles