Can Large Language Models Support Editors Pick Related News Articles?

Editors and journalists play an important role on news platforms. Besides creating trustworthy news stories, they also provide valuable expertise on whichstories are placed on the front page and hand-pick related articles for platformusers to read further. This paper focuses on the specific task of related article selection commonly carried out daily by editors and journalists on news platforms.This is typically a manual process that utilizes an internal search tool to firstfind a pool of potential candidate articles. Then, from those candidate articles,editors and journalists hand-pick the top related articles for a given news articleas a form of expert-selected suggestions for the readers. Although this task canbe an important part of the editorial process in news platforms, it may becometime-consuming and demanding, often requiring significant human effort.In addressing this challenge, we propose an automatic mechanism to supporteditors and journalists in this task by incorporating one of the latest LargeLanguage Models (LLMs), i.e., GPT4o-mini, to shortlist a set of related articlesand recommend them to be checked by journalists and editors. Our evaluationof the proposed approach, based on a real-world dataset from one of the largestcommercial Norwegian news platforms (i.e., TV 2), demonstrates the effectivenessof the approach in supporting editors and journalists in their task of selectingrelevant news articles.