Previous research in multi-document news summarization has typically concentrated on collating information that all sources agree upon. However, to our knowledge, the summarization of diverse information dispersed across multiple articles about an event has not been previously investigated. The latter imposes a different set of challenges for a summarization model. In this paper, we propose a new task of summarizing diverse information encountered in multiple news articles encompassing the same event. To facilitate this task, we outlined a data collection schema for identifying diverse information and curated a dataset named DiverseSumm. The dataset includes 245 news stories, with each story comprising 10 news articles and paired with a human-validated reference. Moreover, we conducted a comprehensive analysis to pinpoint the position and verbosity biases when utilizing Large Language Model (LLM)-based metrics for evaluating the coverage and faithfulness of the summaries, as well as their correlation with human assessments. We applied our findings to study how LLMs summarize multiple news articles by analyzing which type of diverse information LLMs are capable of identifying. Our analyses suggest that despite the extraordinary capabilities of LLMs in single-document summarization, the proposed task remains a complex challenge for them mainly due to their limited coverage, with GPT-4 only able to cover less than 40% of the diverse information on average.

Use this tool to discover more novel angles, voices, and content during content creation. JECT.AI discovers more diverse information to inspire you to create more novel and valuable content. JECT.AI recommends more diverse voices – journalists, scientists and experts based by gender and background – for you to talk to during content creation. JECT.AI offers simple plug-ins that enable you to use its features within your existing work tools. It's not so much a whole new angle that you find but maybe it surfaces a selection of several original and adjacent angles, context and people that you might not have thought of by yourself.

SAN ANTONIO, June 22, 2021 (GLOBE NEWSWIRE) -- CloudCommerce, Inc. (CLWD), a technology driven provider of digital advertising solutions, today announced that SWARM, the Company's AI-driven advertising solution, reduced media costs by more than 60% for Energy in Focus, a web based platform that showcases diverse information on energy in California. Based on the first-round results, the client has committed to a second round. Energy in Focus turned to CloudCommerce to better understand which creative initiatives would be best for their different audiences, such as b2b partners and its public advocacy audience. SWARM analyzed the top 5 previous posts from Facebook and used artificial intelligence to develop creative variations which ran on other media platforms. The result: the cost was reduced by more than 60%.