William Overman

PhD student, Stanford University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

1 paper

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models

#5418 · William Overman, Mohsen Bayati

We introduce a lightweight, post-hoc routing framework, with provable guarantees, that safely delegates between language models with competing objectives.