Papers
arxiv:2306.17806

Stay on topic with Classifier-Free Guidance

Published on Jun 30, 2023
· Submitted by akhaliq on Jul 2, 2023
#1 Paper of the day

Abstract

Classifier-Free Guidance (CFG) has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrate that CFG can be used broadly as an inference-time technique in pure language modeling. We show that CFG (1) improves the performance of Pythia, GPT-2 and LLaMA-family models across an array of tasks: Q\&A, reasoning, code generation, and machine translation, achieving SOTA on LAMBADA with LLaMA-7B over PaLM-540B; (2) brings improvements equivalent to a model with twice the parameter-count; (3) can stack alongside other inference-time methods like Chain-of-Thought and Self-Consistency, yielding further improvements in difficult tasks; (4) can be used to increase the faithfulness and coherence of assistants in challenging form-driven and content-driven prompts: in a human evaluation we show a 75\% preference for GPT4All using CFG over baseline.

Community

Hey, Im reviewing deep learning papers on twitter daily in Hebrew via hashtag #https://twitter.com/hashtag/shorthebrewpapereviews?src=hashtag_click. So far I've shortly reviewed about deep learning papers. You are invited to follow and comment

This paper review can be found at: https://twitter.com/MikeE_3_14/status/1675930643857825792?s=20

Waiting for repo!!

AWESOME WORK, BEST THAT I READ LAST 5+ mounth, simple and effective, wow

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2306.17806 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2306.17806 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2306.17806 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.