Author

Jos'e Hern'andez-Orallo

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.

#artificial intelligence Jan 2026

Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores

This work presents a principled extension of IRT-based adaptive testing to continuous bounded scores to continuous bounded scores (ROUGE, BLEU, LLM-as-a-Judge) by replacing the Bernoulli response distribution with a heteroskedastic normal distribution.

Esma Balkir, Alice Pernthaller, Marco Basaldella et al. · arXiv.org · 5 citations · ⚡1