Research Papers on Auto-Prompting

•

Automatic prompting is one of the hot topics. 4 research papers on auto-prompting and one bonus ▪️ AutoPrompt ▪️ LLMs are Human-Level Prompt Engineers ▪️ Automatic Chain-of-Thought prompting in LLMs ▪️ LLMs are Zero-Shot Reasoners 🎁 Bonus! 🧵

1. AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts Proposes AutoPrompt, a method to automate the creation of prompts based on a gradient-guided search. arxiv.org/pdf/2010.15980.pdf

2. LLMs are Human-Level Prompt Engineers Propose an Automatic Prompt Engineer (APE) method. It outperforms the prior LLM baseline and performs better or comparable to the human-generated instructions. arxiv.org/pdf/2211.01910.pdf

3. Large Language Models are Zero-Shot Reasoners Proposes Zero-shot-CoT, a zero-shot template-based prompting for chain-of-thought reasoning. arxiv.org/pdf/2205.11916.pdf

4. Automatic Chain of Thought Prompting in Large Language Models Proposes an Auto-CoT method automating the Manual-CoT while achieving comparable results. Auto-CoT allows making CoT prompting more scalable and less talent-dependent. openreview.net/pdf?id=5NTt8GFjUHkr

🎁 Bonus! Why think step-by-step? paper Discusses how humans and language models can reason through a series of mental steps, leading to accurate inferences. And compares it to the chain-of-thought reasoning of LMMs. arxiv.org/pdf/2304.03843.pdf