File:Prompting LLMs to respond with quotes directly from pre-training data (Figure 1 from Weller et al. 2023).png

Original file(2,048 × 2,470 pixels, file size: 651 KB, MIME type: image/png)

Summary

Description
English: "Figure 1: Prompting LLMs to respond with quotes directly from pre-training data (shown in purple)." (schematic illustration comparing chatbot answers with and without the "grounding prompt" "According to Wikipedia...")
Date
Source "'According to ...' Prompting Language Models Improves Quoting from Pre-Training Data"
Author Orion Weller, Marc Marone, Nathaniel Weir, Dawn Lawrie, Daniel Khashabi, Benjamin Van Durme

Licensing

w:en:Creative Commons
attribution
This file is licensed under the Creative Commons Attribution 4.0 International license.
You are free:
  • to share – to copy, distribute and transmit the work
  • to remix – to adapt the work
Under the following conditions:
  • attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.

Captions

Add a one-line explanation of what this file represents

Items portrayed in this file

depicts

22 May 2023

image/png

File history

Click on a date/time to view the file as it appeared at that time.

Date/TimeThumbnailDimensionsUserComment
current21:34, 16 July 2023Thumbnail for version as of 21:34, 16 July 20232,048 × 2,470 (651 KB)HaeBUploaded a work by Orion Weller, Marc Marone, Nathaniel Weir, Dawn Lawrie, Daniel Khashabi, Benjamin Van Durme from "[https://arxiv.org/abs/2305.13252 'According to ...' Prompting Language Models Improves Quoting from Pre-Training Data]" with UploadWizard
The following pages on the English Wikipedia use this file (pages on other projects are not listed):

Global file usage

The following other wikis use this file:

Metadata