ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2408.09742
17
0
v1v2 (latest)

Paired Completion: Flexible Quantification of Issue-framing at Scale with LLMs

19 August 2024
Simon D Angus
Lachlan O’Neill
ArXiv (abs)PDFHTML
Main:7 Pages
7 Figures
Bibliography:3 Pages
11 Tables
Appendix:26 Pages
Abstract

Detecting issue framing in text - how different perspectives approach the same topic - is valuable for social science and policy analysis, yet challenging for automated methods due to subtle linguistic differences. We introduce `paired completion', a novel approach using LLM next-token log probabilities to detect contrasting frames using minimal examples. Through extensive evaluation across synthetic datasets and a human-labeled corpus, we demonstrate that paired completion is a cost-efficient, low-bias alternative to both prompt-based and embedding-based methods, offering a scalable solution for analyzing issue framing in large text collections, especially suited to low-resource settings.

View on arXiv
@article{angus2025_2408.09742,
  title={ Paired Completion: Flexible Quantification of Issue-framing at Scale with LLMs },
  author={ Simon D Angus and Lachlan OÑeill },
  journal={arXiv preprint arXiv:2408.09742},
  year={ 2025 }
}
Comments on this paper