Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions Paper • 2605.10664 • Published 3 days ago • 7
Optimizing Decomposition for Optimal Claim Verification Paper • 2503.15354 • Published Mar 19, 2025 • 18
IHEval: Evaluating Language Models on Following the Instruction Hierarchy Paper • 2502.08745 • Published Feb 12, 2025 • 20