Jan 02, 2025 Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection Apr 13, 2024 Scaling Laws for Data Filtering— Data Curation cannot be Compute Agnostic Sep 19, 2023 The CRINGE Loss: Learning what language not to model Sep 12, 2023 SILO LANGUAGE MODELS: ISOLATING LEGAL RISK IN A NONPARAMETRIC DATASTORE Feb 09, 2023 AdapterHub: A Framework for Adapting Transformers, Parameter-Efficient Transfer Learning for NLP