Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language Paper • 2510.23828 • Published Oct 27, 2025 • 1
Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language Paper • 2510.23828 • Published Oct 27, 2025 • 1 • 1
RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models Paper • 2510.10390 • Published Oct 12, 2025 • 4
RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models Paper • 2510.10390 • Published Oct 12, 2025 • 4 • 2
SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs Paper • 2504.08192 • Published Apr 11, 2025 • 3
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs Paper • 2505.20254 • Published May 26, 2025 • 5
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs Paper • 2505.20254 • Published May 26, 2025 • 5
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs Paper • 2505.20254 • Published May 26, 2025 • 5 • 1