Author

Bahareh Sarrafzadeh

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... Aug 2025

Evaluating Style-Personalized Text Generation: Challenges and Directions

This work critically examines the effectiveness of the most common metrics used in the field, such as BLEU, embeddings, and LLMs-as-judges, and finds strong evidence that employing ensembles of diverse evaluation metrics consistently outperforms single-evaluator methods.

Anubhav Jangra, Bahareh Sarrafzadeh, Adrian de Wynter et al. · arXiv.org · 2 citations