Tag
The paper introduces NarrativeBench, a benchmark of 1,333 news articles in 23 languages and 460 queries, evaluating 14 LLMs and finding they cannot reliably help users navigate diverse multilingual narratives, risking echo chambers and information disparities.
This paper investigates whether large language models generate diverse stories. Using narrative similarity analysis, the authors find that LLM-generated narratives are consistently more similar to each other than human-written stories, and that common mitigation strategies like negative prompting and temperature scaling fail to address this homogeneity.