Awesome GPT Prompt Engineering
Section: Papers
SlowScore 65
Entry
Self-Consistency Improves Chain of Thought Reasoning in Language Models
Appears in 5 awesome lists
Multi-path sampling + majority vote: GSM8K 57% → 74%
Found in these lists
Awesome LLM Reasoning
Section: 2023
ActiveScore 69
awesome-nlp
Section: Reasoning and Test-Time Compute · majority vote over sampled CoT chains.
FreshScore 90
Awesome Prompts
Section: Foundations · Multi-path sampling + majority vote: GSM8K 57% → 74%
FreshScore 90
awesome-chatgpt
Section: Recent advances in Prompt engineering
StaleScore 52
Often listed next to it
ReAct
The foundational paper defining the Thought/Action/Observation loop structure that underlies virtually every agent harness. Required reading for understanding why the loop is structured the way it is and where each harness component maps onto the reasoning-acting cycle.
In 7 listsDetails
Attention Is All You Need
(AIAYN) - Introducing multi-head self-attention neural networks with positional encoding to do sentence-level NLP without any RNN nor CNN - this paper is a must-read (also see this explanation and this visualization of the paper).
In 6 listsDetails
Chain-of-Thought Prompting
foundational result; intermediate reasoning steps improve performance.
In 5 listsDetails
Large Language Models are Zero-Shot Reasoners
"Let's think step by step" — zero-shot CoT milestone
In 4 listsDetails
Tree of Thoughts
search over reasoning trees.
In 4 listsDetails
Language Models are Few-Shot Learners
by Tom B. Brown (OpenAI) et al. - "We train GPT-3, an autoregressive language model with 175 billion parameters :scream:, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting."
In 4 listsDetails
Constitutional AI
A method for training helpful and harmless AI assistants using written principles.
In 3 lists
APE: Human-Level Prompt Engineers (2023)
LLM auto-generates and selects instructions — beats human prompts
In 2 lists