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

Anonymous

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$^3$Sum, a diffusion model-based summarization approach controlled by political perspective classifiers. InP$^3$Sum, the political leaning of a generated summary is iteratively evaluated at each decoding step, and any drift from the article's original stance incurs a loss back-propagated to the embedding layers, steering the political stance of the summary at inference time. Extensive experiments on three news summarization datasets demonstrate that P$^3$Sum outperforms state-of-the-art summarization systems and large language models by up to $11.4\%$ in terms of the success rate of stance preservation, with competitive performance on standard metrics of summarization quality. Our findings present a first analysis of preservation of pragmatic features in summarization, highlight the lacunae in existing summarization models---that even state-of-the-art models often struggle to preserve author's intents---and develop new summarization systems that are more faithful to author's perspectives.

Paper Type: long

Research Area: Summarization

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

Languages Studied: English