Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pappone, Francesco, Lazzaroni, Ruggero Marino, Califano, Federico, Gentile, Niccolò, Marras, Roberto
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!