English

Multi-Layer Ranking with Large Language Models for News Source Recommendation

Information Retrieval 2024-06-18 v1 Computation and Language

Abstract

To seek reliable information sources for news events, we introduce a novel task of expert recommendation, which aims to identify trustworthy sources based on their previously quoted statements. To achieve this, we built a novel dataset, called NewsQuote, consisting of 23,571 quote-speaker pairs sourced from a collection of news articles. We formulate the recommendation task as the retrieval of experts based on their likelihood of being associated with a given query. We also propose a multi-layer ranking framework employing Large Language Models to improve the recommendation performance. Our results show that employing an in-context learning based LLM ranker and a multi-layer ranking-based filter significantly improve both the predictive quality and behavioural quality of the recommender system.

Keywords

Cite

@article{arxiv.2406.11745,
  title  = {Multi-Layer Ranking with Large Language Models for News Source Recommendation},
  author = {Wenjia Zhang and Lin Gui and Rob Procter and Yulan He},
  journal= {arXiv preprint arXiv:2406.11745},
  year   = {2024}
}

Comments

Accepted by the SIGIR 2024. arXiv admin note: text overlap with arXiv:2305.04825

R2 v1 2026-06-28T17:08:57.874Z