Generative AI/Prompt Engineering
- True Detective: A Deep Abductive Reasoning BenchmarkUndoable for GPT-3 and Challenging for GPT-4 2024.10.18
- Large Language Models as Analogical Reasoners 2024.10.18
- Take a Step back: Evoking Reasoning via Abstraction in Large Language Models 2024.10.17
- Large Language Models are Zero-Shot Reasoners 2024.10.17
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models 2024.10.16
- Re-Reading Improves Reasoning in Large Language Models 2024.10.12
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent debate 2024.10.10
- Evaluation Tips 2024.10.10
- Many-Shot In-Context Learning 2024.10.09
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models 2024.10.08