Uncovering the Bigger Picture: Comprehensive Event Understanding Via Diverse News Retrieval

ACL ARR 2025 May Submission2879 Authors

Abstract: Access to diverse perspectives is essential for understanding real-world events, yet most news retrieval systems prioritize textual relevance, leading to redundant results and limited viewpoint exposure. We propose **NEWSCOPE**, a two-stage framework for diverse news retrieval that enhances event coverage by explicitly modeling semantic variation at the sentence level. The first stage retrieves topically relevant content using dense retrieval, while the second stage applies sentence-level clustering and diversity-aware re-ranking to surface complementary information. To evaluate retrieval diversity, we introduce three interpretable metrics, namely Average Pairwise Distance, Positive Cluster Coverage, and Information Density Ratio, and construct two paragraph-level benchmarks: **LocalNews** and **DSGlobal**. Experiments show that NEWSCOPE consistently outperforms strong baselines, achieving significantly higher diversity without compromising relevance. Our results demonstrate the effectiveness of fine-grained, interpretable modeling in mitigating redundancy and promoting comprehensive event understanding. We will release both the benchmark and code upon publication.

Paper Type: Long

Research Area: Information Retrieval and Text Mining

Research Area Keywords: passage retrieval; re-ranking; quantitative analyses of news and/or social media

Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English

Submission Number: 2879