CLLGNov 16, 2023

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

CMU
arXiv:2311.09741v27 citationsh-index: 27
Originality Incremental advance
AI Analysis

It addresses the issue of misrepresenting authors' intents in summarization for news readers and AI applications, presenting a novel approach but focusing on a specific domain.

The paper tackles the problem of preserving authors' political perspectives in news summarization, finding that existing approaches alter stances in over 50% of summaries, and proposes P^3SUM, which improves stance preservation success rate by up to 13.7% compared to state-of-the-art systems.

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 summarization approach controlled by political perspective classifiers. In P^3SUM, 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^3SUM outperforms state-of-the-art summarization systems and large language models by up to 13.7% 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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes