From the 1 of 8 linked papers with an AI index.
8 papers
Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards
Yuxuan Zhu, Rohan Alur, Daniel Kang
The paper derives the first non‑vacuous PAC‑Bayes generalization bounds for parameter‑efficient reinforcement learning with verifiable rewards applied to billion‑parameter language…
The Impossibility of Inverse Permutation Learning in Transformer Models
Rohan Alur, Chris Hays, Manish Raghavan +1
In this technical note, we study the problem of inverse permutation learning in decoder-only transformers. Given a permutation and a string to which that permutation has been appli…
AIA Forecaster: Technical Report
Rohan Alur, Bradly C. Stadie, Daniel Kang +11
This technical report describes the AIA Forecaster, a Large Language Model (LLM)-based system for judgmental forecasting using unstructured data. The AIA Forecaster approach combin…
Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
Vinith M. Suriyakumar, Rohan Alur, Ayush Sekhari +2
Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make increm…
Auditing for Human Expertise
Rohan Alur, Loren Laine, Darrick K. Li +3
High-stakes prediction tasks (e.g., patient diagnosis) are often handled by trained human experts. A common source of concern about automation in these settings is that experts may…
Human Expertise in Algorithmic Prediction
Rohan Alur, Manish Raghavan, Devavrat Shah
We introduce a novel framework for incorporating human expertise into algorithmic predictions. Our approach leverages human judgment to distinguish inputs which are algorithmically…