PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation Paper • 2601.18006 • Published May 27 • 4
🍐PEAR Collection Paper, model checkpoints, and data for 🍐PEAR, a reference-free pairwise MT evaluation model presented at ACL 2026. • 4 items • Updated about 6 hours ago • 6
ClaimExtractor-2605 Collection Extract claims and intents from conversations • 7 items • Updated Jun 14 • 8
Translation Difficulty Estimators Collection This collection hosts the two Translation Difficulty estimators studied in the EMNLP 2025 publication https://aclanthology.org/2025.findings-emnlp. • 3 items • Updated 6 days ago • 3
Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation Paper • 2504.17025 • Published Apr 23, 2025 • 17