Trending

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

Added to collectionMaybe Cool

Artificial Intelligence

Computation and Language

Self-consistency: Improving the Accuracy of Large Language Models

Self-Consistency Improves Chain of Thought Reasoning in Language Models

We explore a simple ensemble strategy, self-consistency, that significantly improves the reasoning accuracy of large language models.

The idea is to sample a diverse set of outputs from a language model and return the most consistent answer in the set.

Such ensembling method improves reasoning accuracy when combined with chain of thought prompting.

For arithmetic and commonsense reasoning benchmarks we find that self-consistency yields significant accuracyimprovements in a variety of datasets, such as gsm8k, svamp, multiarith, commonsenseqa and arc.

Authors

Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Denny Zhou

Related Topics

Large language models

Ensemble strategy

Self-consistency

Ensembling method

Read the Paper

Read Paper

Trending

Bookmarks

◐ Recommended Follows

Founder 42papers.com. Also bui...

Average CS student at ULL. I l...

Vojtěch Létal

More

◐ Latest Activity

More

Self-consistency: Improving the Accuracy of Large Language Models - 42Papers

Read Related Papers

A Worker-Task Specialization Model for Crowdsourcing: Efficient Inference and Fundamental Limits

TraVLR: Now You See It, Now You Don't! Evaluating Cross-Modal Transfer of Visio-Linguistic Reasoning

Knowledge Based Multilingual Language Model

The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection

Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks

Teaching Humans When To Defer to a Classifier via Examplars

Crossing the Format Boundary of Text and Boxes: Towards Unified Vision-Language Modeling

Zero-Shot Open-Book Question Answering

Language-agnostic BERT Sentence Embedding

Multi-modal Vision Transformers for Object Detection