ReflCtrl: Controlling LLM Reflection via Representation Engineering Paper • 2512.13979 • Published Dec 16, 2025
Interpretable Generative Models through Post-hoc Concept Bottlenecks Paper • 2503.19377 • Published Mar 25, 2025
LLM Agents Already Know When to Call Tools -- Even Without Reasoning Paper • 2605.09252 • Published 7 days ago • 1
LLM Agents Already Know When to Call Tools -- Even Without Reasoning Paper • 2605.09252 • Published 7 days ago • 1
LLM Agents Already Know When to Call Tools -- Even Without Reasoning Paper • 2605.09252 • Published 7 days ago • 1
Steer2Edit: From Activation Steering to Component-Level Editing Paper • 2602.09870 • Published Feb 10 • 1
Steer2Edit: From Activation Steering to Component-Level Editing Paper • 2602.09870 • Published Feb 10 • 1
Steer2Edit: From Activation Steering to Component-Level Editing Paper • 2602.09870 • Published Feb 10 • 1
ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability Paper • 2510.09062 • Published Oct 10, 2025 • 2 • 2
ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability Paper • 2510.09062 • Published Oct 10, 2025 • 2
ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability Paper • 2510.09062 • Published Oct 10, 2025 • 2