BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation Paper โข 2604.09497 โข Published 8 days ago โข 28 โข 3
When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance Paper โข 2509.22193 โข Published Sep 26, 2025 โข 38 โข 3
Should We Still Pretrain Encoders with Masked Language Modeling? Paper โข 2507.00994 โข Published Jul 1, 2025 โข 81 โข 9
Should We Still Pretrain Encoders with Masked Language Modeling? Paper โข 2507.00994 โข Published Jul 1, 2025 โข 81 โข 9
Should We Still Pretrain Encoders with Masked Language Modeling? Paper โข 2507.00994 โข Published Jul 1, 2025 โข 81 โข 9