English

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

Computation and Language 2025-06-13 v2 Artificial Intelligence General Economics Economics

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.

Keywords

Cite

@article{arxiv.2408.09742,
  title  = {Paired Completion: Flexible Quantification of Issue-framing at Scale with LLMs},
  author = {Simon D Angus and Lachlan O'Neill},
  journal= {arXiv preprint arXiv:2408.09742},
  year   = {2025}
}

Comments

9 pages, 4 figures

R2 v1 2026-06-28T18:16:22.027Z