P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models

arXiv:2311.09741v2 Announce Type: replace-cross
Abstract: In this work, we take a first step towards designing summarization systems that are faithful to the author's intent, not only the semantic content of the article. Focusing on a case study of preserving political perspectives in news summarization, we find that existing approaches alter the political opinions and stances of news articles in more than 50% of summaries, misrepresenting the intent and perspectives of the news authors. We thus propose P^3SUM, a diffusion model-based …

abstract article arxiv author case case study cs.cl cs.lg designing diffusion language language models perspective perspectives political semantic study summarization systems type work