BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation Paper β’ 2604.09497 β’ Published 26 days ago β’ 29 β’ 3
When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance Paper β’ 2509.22193 β’ Published Sep 26, 2025 β’ 38 β’ 3
Should We Still Pretrain Encoders with Masked Language Modeling? Paper β’ 2507.00994 β’ Published Jul 1, 2025 β’ 81 β’ 9
Should We Still Pretrain Encoders with Masked Language Modeling? Paper β’ 2507.00994 β’ Published Jul 1, 2025 β’ 81 β’ 9
Should We Still Pretrain Encoders with Masked Language Modeling? Paper β’ 2507.00994 β’ Published Jul 1, 2025 β’ 81 β’ 9