Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation Paper • 2512.13655 • Published 21 days ago • 2
Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation Paper • 2512.13655 • Published 21 days ago • 2
Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks Paper • 2511.22047 • Published Nov 27, 2025
Comparative Analysis of LoRA-Adapted Embedding Models for Clinical Cardiology Text Representation Paper • 2511.19739 • Published Nov 24, 2025
Vision Token Masking Alone Cannot Prevent PHI Leakage in Medical Document OCR: A Systematic Evaluation Paper • 2511.18272 • Published Nov 23, 2025
CardioEmbed: Domain-Specialized Text Embeddings for Clinical Cardiology Paper • 2511.10930 • Published Nov 14, 2025
When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs Paper • 2510.18892 • Published Oct 18, 2025