From the 1 of 6 linked papers with an AI index.
6 papers
Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning
Keegan Harris, Brian W. Lee, Ian Waudby-Smith +3
The paper introduces a game‑theoretic framework for RL fine‑tuning that determines the KL regularization coefficient by treating the trade‑off between reward and deviation from a r…
Should You Use Your Large Language Model to Explore or Exploit?
Keegan Harris, Aleksandrs Slivkins
We evaluate the ability of the current generation of large language models (LLMs) to help a decision-making agent facing an exploration-exploitation tradeoff. While previous work h…
In-Context Credit Assignment via the Core
Keegan Harris, Siddharth Prasad, Asher Trockman
We propose incentive-aligned mechanisms for in-context credit assignment: the task of assigning credit for AI-generated content (e.g. code, news articles, short-form videos) among…
Can ChatGPT Learn My Life From a Week of First-Person Video?
Keegan Harris
Motivated by recent improvements in generative AI and wearable camera devices (e.g. smart glasses and AI-enabled pins), I investigate the ability of foundation models to learn abou…
Algorithmic Persuasion Through Simulation
Keegan Harris, Nicole Immorlica, Brendan Lucier +1
We study a Bayesian persuasion game where a sender wants to persuade a receiver to take a binary action, such as purchasing a product. The sender is informed about the (real-valued…
Can large language models explore in-context?
Akshay Krishnamurthy, Keegan Harris, Dylan J. Foster +2
We investigate the extent to which contemporary Large Language Models (LLMs) can engage in exploration, a core capability in reinforcement learning and decision making. We focus on…