Skip to content
Awesomelist
Type at least 2 letters

Search entries, descriptions and list names. Press Esc to close.

Arrow keys move, Enter opensFull search page

Entry

Chain-of-Thought Prompting

Appears in 5 awesome lists

foundational result; intermediate reasoning steps improve performance.

Open arxiv.org

Found in these lists

Awesome AI Papers

Section: NLP

SlowScore 51

Awesome GPT Prompt Engineering

Section: Papers

SlowScore 65

Awesome LLM Reasoning

Section: 2022 · [blog]

ActiveScore 69

awesome-nlp

Section: Reasoning and Test-Time Compute · foundational result; intermediate reasoning steps improve performance.

FreshScore 90

awesome-chatgpt

Section: Recent advances in Prompt engineering

StaleScore 52

ChatGPT

Announcement of ChatGPT, a conversational model trained to answer follow-up questions, admit mistakes, challenge incorrect premises, and reject inappropriate requests. OpenAI blog, November 30, 2022.

In 8 listsDetails

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

Training language models to follow instructions with human feedback

This paper presents an RLHF approach to using supervised learning to fine-tuning. It is also known as a paper that illustrates the kernel of ChatGPT's thinking. Presumably, ChatGPT is an extended version of InstructGPT that enables fine-tuning on larger datasets.

In 6 listsDetails

Self-Consistency Improves Chain of Thought Reasoning in Language Models

Multi-path sampling + majority vote: GSM8K 57% → 74%

In 5 listsDetails

Large Language Models are Zero-Shot Reasoners

"Let's think step by step" — zero-shot CoT milestone

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