William M Wells — accepted AI-conference papers

2025

Calibrating Expressions of Certainty

Peiqi Wang, Barbara D. Lam, Yingcheng Liu, Ameneh Asgari-Targhi, Rameswar Panda, William M Wells +2

ICLR 2025poster

We present a novel approach to calibrating linguistic expressions of certainty, e.g., "Maybe" and "Likely". Unlike prior work that assigns a single score to each certainty phrase, we model uncertainty as distributions over the simplex to capture their semantics more accurately. To accommodate this n…

Cited by 9 Source ↗PDF ↗Scholar ↗

2025

Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning

Reuben Dorent, Polina Golland, William M Wells

NeurIPS 2025poster

Mutual Information (MI) is a fundamental measure of statistical dependence widely used in representation learning. While direct optimization of MI via its definition as a Kullback-Leibler divergence (KLD) is often intractable, many recent methods have instead maximized alternative dependence measure…

Cited by 0 Source ↗Scholar ↗