This repository serves as a curated collection of research papers focused on "Chain of Thought" (CoT) prompting and its advancements in Large Language Models (LLMs). It aims to track the evolution of CoT, providing a valuable resource for researchers and practitioners in Natural Language Processing (NLP) and AI.

How It Works

The repository lists seminal and recent papers that explore CoT prompting, a technique that elicits reasoning capabilities in LLMs by guiding them to generate intermediate steps. It covers various aspects, including self-consistency, tool use, multimodal reasoning, and applications in diverse domains like mathematics and code.

Quick Start & Requirements

• No installation or execution required; this is a reference list.
• Links to papers (PDFs), code repositories, and blogs are provided for each entry.

Highlighted Details

• Comprehensive list of papers from 2022-2023, covering foundational CoT work and subsequent developments.
• Includes links to associated code and supplementary materials where available.
• Highlights key research directions such as Self-Consistency, STaR, Minerva, ReAct, and Multimodal CoT.

Maintenance & Community

• The repository is maintained by Timothyxxx.
• No specific community channels or active development discussions are indicated.

Licensing & Compatibility

• The repository itself does not appear to have a specific license; it is a collection of links to external research papers.
• Compatibility is with accessing external research content.

Limitations & Caveats

• This is a static list of papers and does not include any executable code or interactive demos.
• The focus is solely on Chain-of-Thought prompting, with other LLM research areas not covered.