Author

Zoë Prins

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Mar 2026

Is my model perplexed for the right reason? Contrasting LLMs' Benchmark Behavior with Token-Level Perplexity

A simple, principled interpretability framework based on token-level perplexity to test whether models rely on linguistically relevant cues is introduced, revealing that models rely on heuristics other than the expected linguistic ones.

Zoë Prins, Samuele Punzo, Frank Wildenburg et al. · arXiv.org · 1 citation