The Geometry of Truth: Emergent Linear Structure in LLM Representation of True/False DatasetsNovember 30, 2023
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning November 20, 2023
RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language ModelsOctober 18, 2023
Explaining Grokking Through Circuit Efficiency October 17, 2023
Large Content And Behavior Models To Understand, Simulate, And Optimize Content And BehaviorSeptember 29, 2023
Skeleton of Thought: LLMs Can Do Parallel Decoding August 30, 2023
Llama 2: Open Foundation and Fine-Tuned Chat ModelsJuly 31, 2023
Lost in the Middle: How Language Models Use Long ContextsJuly 26, 2023
Orca: Progressive Learning from Complex Explanation Traces of GPT-4 July 21, 2023
Toolformer: Training LLMs To Use ToolsMarch 20, 2023
Hungry Hungry Hippos - H3February 13, 2023
ChatGPT and InstructGPT: Aligning Language Models to Human IntentionJanuary 18, 2023