Cite
Notes
Only stored in your browser.
Attribution
BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation
arXiv 2026
Should We Still Pretrain Encoders with Masked Language Modeling?
arXiv 2025
Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism
arXiv 2024
from 3 papers
Céline Hudelot
Hippolyte Gisserot-Boukhlef
Pierre Colombo
Manuel Faysse
Nicolas Boizard
André F. T. Martins
Duarte M. Alves