Skip to content

Entry

Self-Consistency Improves Chain of Thought Reasoning in Language Models

Appears in 6 awesome lists

Samples diverse reasoning paths and selects their most consistent answer to improve inference-time reliability. (ICLR 2023)

Open arxiv.org

Found in these lists

Awesome GPT Prompt Engineering

Section: Papers

SlowScore 62

Awesome LLM Reasoning

Section: 2023

SlowScore 72

awesome-nlp

Section: Reasoning and Test-Time Compute · majority vote over sampled CoT chains.

FreshScore 91

Awesome Prompts

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

FreshScore 96

Awesome RSI (Recursive Self-Improvement)

Section: Self-Verification & Self-Correction — Enabling Foundations · Samples diverse reasoning paths and selects their most consistent answer to improve inference-time reliability. (ICLR 2023)

FreshScore 85

awesome-chatgpt

Section: Recent advances in Prompt engineering

StaleScore 46

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 lists

Constitutional AI

Uses written principles and model-generated critiques to scale supervision while retaining explicit behavioral constraints. (arXiv 2022)

In 4 lists

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 lists

rStar-Math

(2025) - small policy model paired with a process preference model trained via MCTS rollouts; enables small LMs to bootstrap reasoning without distilling from larger models.

In 3 lists