today local_bar

Thomas P Zollo

PhD student, Columbia University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Guiding LLM Decision-Making with Fairness Reward Models

#1113 · Zara Hall, Melanie Subbiah, Thomas P Zollo, Kathleen McKeown, Richard Zemel

We train reward models to encourage fairer step-by-step reasoning in LLMs, reducing bias on high-stakes decision-making tasks