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

arXiv: https://arxiv.org/abs/2508.19758 · HTML: https://mlsanity.com/paper/2508.19758/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks](https://mlsanity.com/paper/2010.08240/) (2020)
- [Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles](https://mlsanity.com/paper/2309.09369/) (2023)
- [Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs](https://mlsanity.com/paper/2408.12060/) (2024)
- [Fair Abstractive Summarization of Diverse Perspectives](https://mlsanity.com/paper/2311.07884/) (2023)
- [Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence](https://mlsanity.com/paper/2503.05037/) (2025)
- [MetaSumPerceiver: Multimodal Multi-Document Evidence Summarization for Fact-Checking](https://mlsanity.com/paper/2407.13089/) (2024)
- [Diversity-Aware k-Maximum Inner Product Search Revisited](https://mlsanity.com/paper/2402.13858/) (2024)
- [The Missing Parts: Augmenting Fact Verification with Half-Truth Detection](https://mlsanity.com/paper/2508.00489/) (2025)
- [Deception through Half-Truths](https://mlsanity.com/paper/1911.05885/) (2019)
- [Contrastive Learning to Improve Retrieval for Real-world Fact Checking](https://mlsanity.com/paper/2410.04657/) (2024)
- [Give Me More Details: Improving Fact-Checking with Latent Retrieval](https://mlsanity.com/paper/2305.16128/) (2023)
- [Community Fact-Checks Trigger Moral Outrage in Replies to Misleading Posts on Social Media](https://mlsanity.com/paper/2409.08829/) (2024)
- [PerspectroScope: A Window to the World of Diverse Perspectives](https://mlsanity.com/paper/1906.04761/) (2019)
- [Crowd Intelligence for Early Misinformation Prediction on Social Media](https://mlsanity.com/paper/2408.04463/) (2024)
- [Finding Convincing Views to Endorse a Claim](https://mlsanity.com/paper/2408.14974/) (2024)

## Built on by (most cited first, 4 of 4)

- [AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAG](https://mlsanity.com/paper/2512.25052/) (2025)
- [Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos](https://mlsanity.com/paper/2601.06931/) (2026)
- [DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval](https://mlsanity.com/paper/2605.31377/) (2026)
- [MegaStyle++: Scaling Image Style Space through Hierarchical Style Definition](https://mlsanity.com/paper/2609.01423/) (2026)

## Abstract (arXiv)

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. The data and code are available at https://github.com/tangyixuan/NEWSCOPE.