← Search

Jihan Yao

2 accepted papers

2025

POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition

ICLR 2025spotlight

We study off-policy learning (OPL) of contextual bandit policies in large discrete action spaces where existing methods -- most of which rely crucially on reward-regression models or importance-weighted policy gradients -- fail due to excessive bias or variance. To overcome these issues in OPL, we p…

Cited by 0SourcePDFScholar
2025

Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only

ICLR 2025poster

In the absence of abundant reliable annotations for challenging tasks and contexts, how can we expand the frontier of LLM capabilities with potentially wrong answers? We focus on two research questions: (1) Can LLMs generate reliable preferences among wrong options? And if so, (2) Would alignment wi…