OCC-RAG: Optimal Cognitive Core for Faithful Question Answering Paper • 2606.00683 • Published 6 days ago • 81
OCC-RAG Collection OCC-RAG: Optimal Cognitive Core models for faithful, context-grounded question answering. • 2 items • Updated 1 day ago • 18
Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures Paper • 2603.16475 • Published Mar 17 • 13
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? Paper • 2602.14111 • Published Feb 15 • 56
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? Paper • 2602.14111 • Published Feb 15 • 56
GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms Paper • 2511.17592 • Published Nov 17, 2025 • 121
GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms Paper • 2511.17592 • Published Nov 17, 2025 • 121
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs Paper • 2510.11288 • Published Oct 13, 2025 • 48
The Rogue Scalpel: Activation Steering Compromises LLM Safety Paper • 2509.22067 • Published Sep 26, 2025 • 28