LoRA
From the wire
Original publisher articles citing LoRA. Broadside has not yet written editorial coverage for these.
To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Embeddings, Except In Heavy Truncation Scenarios
Comparing LLM and Fine-Tuned Model Performance on NVDRS Circumstance Extraction with Varying Prompt Complexity
Do LLMs Know What Luxembourgish Borrows? Probing Lexical Neology in Low-Resource Multilingual Models
Responsible Federated LLMs via Safety Filtering and Constitutional AI
Distractions