TL;DR — Authorship requires both earning it and being able to defend the work.

TL;DR — Developing useful evaluations requires clarity about what exactly one is trying to learn about a phenomenon of interest.

TL;DR — Because unobservable constructs hold ‘surplus meaning,’ your metric is not your construct.

TL;DR — Poor conceptual foundations can severely undermine the credibility and reliability of knowledge claims. (And, no, your metric is not your construct.)

Pairwise comparisons combined with aggregation methods like Elo have become central to evaluating generative models, yet concerns remain that they reward superficial stylistic cues or display judge bi...

YouTube video by Microsoft Research

In AI research and practice, rigor remains largely understood in terms of methodological rigor -- such as whether mathematical, statistical, or computational methods are correctly applied. We argue th...

In AI research and practice, rigor remains largely understood in terms of methodological rigor -- such as whether mathematical, statistical, or computational methods are correctly applied. We argue th...