Precise In-Parameter Concept Erasure in Large Language Models Paper • 2505.22586 • Published May 28, 2025 • 1
Dissecting Fine-Tuning Unlearning in Large Language Models Paper • 2410.06606 • Published Oct 15, 2024
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction Paper • 2503.23084 • Published Mar 29, 2025
Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment Paper • 2609.38972 • Published 8 days ago • 12
Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment Paper • 2609.38972 • Published 8 days ago • 12
Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment Paper • 2609.38972 • Published 8 days ago • 12
YihuaiHong/MEMIT_Empty_unlearn_on_Ancient-Rome_concept_llama3.1-8b-instruct 8B • Updated May 18, 2025 • 7
YihuaiHong/MEMIT_Empty_unlearn_on_Ancient-Rome_concept_llama3.1-8b-instruct 8B • Updated May 18, 2025 • 7
YihuaiHong/MEMIT_Empty_unlearn_on_Culture-of-Greece_concept_llama3.1-8b-instruct 8B • Updated May 18, 2025 • 2
YihuaiHong/MEMIT_Empty_unlearn_on_Culture-of-Greece_concept_llama3.1-8b-instruct 8B • Updated May 18, 2025 • 2
YihuaiHong/MEMIT_Empty_unlearn_on_Republic-of-Ireland_concept_llama3.1-8b-instruct 8B • Updated May 18, 2025 • 2
YihuaiHong/MEMIT_Empty_unlearn_on_Republic-of-Ireland_concept_llama3.1-8b-instruct 8B • Updated May 18, 2025 • 2
YihuaiHong/MEMIT_Empty_unlearn_on_Harry-Potter_concept_llama3.1-8b-instruct 8B • Updated May 18, 2025 • 5
YihuaiHong/MEMIT_Empty_unlearn_on_Harry-Potter_concept_llama3.1-8b-instruct 8B • Updated May 18, 2025 • 5
YihuaiHong/MEMIT_Empty_unlearn_on_Baseball_concept_llama3.1-8b-instruct 8B • Updated May 18, 2025 • 4
YihuaiHong/MEMIT_Empty_unlearn_on_Baseball_concept_llama3.1-8b-instruct 8B • Updated May 18, 2025 • 4