## Prompt testing - TypeScript [promptfoo](https://www.promptfoo.dev/) - Python [PromptTools](https://github.com/hegelai/prompttools) - Python [PromptFlow](https://microsoft.github.io/promptflow/) ## Prompt design - Zero-shot Chain-of-Thought baseline: [Chain-of-Thought Prompting](Chain-of-Thought%20Prompting.md) - Few-shot Chain-of-Thought: [Plan-and-Solve Prompting](Plan-and-Solve%20Prompting.md) - Retrieval-Augmented Generation: [RAG for Knowledge-Intensive NLP Tasks](https://proceedings.neurips.cc/paper/2020/file/6b493230205f780e1bc26945df7481e5-Paper.pdf) - Reasoning & Acting: [ReAct Prompting](ReAct%20Prompting.md) ## Prompt tuning - Prefix Tuning: [Optimizing Continuous Prompts for Generation](https://aclanthology.org/2021.acl-long.353/) - Prompt Tuning: [The Power of Scale for Parameter-Efficient Prompt Tuning](Prompt%20Tuning.md) - P-Tuning: [GPT Understands, Too](P-Tuning.md) ## Prompt optimization - AutoPrompt: [Eliciting Knowledge from Language Models with Automatically Generated Prompts](https://aclanthology.org/2020.emnlp-main.346/) - APO: [Automatic Prompt Optimization with “Gradient Descent” and Beam Search](https://arxiv.org/abs/2305.03495) - APE: [Large Langauge Models are Human-level Prompt Engineers](Automatic%20Prompt%20Engineer%20(APE).md) - OPRO: [OPRO - Large Language Models as Optimizers](OPRO%20-%20Large%20Language%20Models%20as%20Optimizers.md) ## Model tuning - Distilling: [Distilling Step-by-Step](Distilling%20Step-by-Step.md) - Finetuning: [Large Language Models can Self-improve](https://openreview.net/forum?id=NiEtU7blzN) - Low-Rank Adaptation: [QLoRA: Efficient Finetuning of Quantized LLMs](https://arxiv.org/abs/2305.14314)