News is More than a Collection of Facts: Moral Frame Preserving News Summarization

2025-04-01

AI Summary

Existing news automatic summarization systems frequently neglect the moral framing present in source texts, resulting in the loss of morally loaded vocabulary and distortion of authorial intent. Method: This paper formally defines the “moral framing preservation” task for the first time and proposes a novel controllable summarization paradigm that jointly optimizes moral term retention and summary quality. The approach integrates prompt engineering, a fine-grained moral term identification module, and controllable generation techniques, supported by a tripartite evaluation framework combining automated metrics, crowdsourcing, and expert annotation. Results: Experiments demonstrate a 27.3% improvement in moral framing preservation rate, with no degradation in ROUGE-L scores or human evaluation ratings—validating both effectiveness and practicality. The core contribution is establishing moral sensitivity as a new dimension of summary quality and delivering the first evaluable, reproducible solution for moral framing preservation.

Technology Category

• Natural Language Processing: Summarization
• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

News articles are more than collections of facts; they reflect journalists' framing, shaping how events are presented to the audience. One key aspect of framing is the choice to write in (or quote verbatim) morally charged language as opposed to using neutral terms. This moral framing carries implicit judgments that automated news summarizers should recognize and preserve to maintain the original intent of the writer. In this work, we perform the first study on the preservation of moral framing in AI-generated news summaries. We propose an approach that leverages the intuition that journalists intentionally use or report specific moral-laden words, which should be retained in summaries. Through automated, crowd-sourced, and expert evaluations, we demonstrate that our approach enhances the preservation of moral framing while maintaining overall summary quality.

Problem

• Preserve moral framing in AI-generated news summaries
• Recognize and retain journalists' implicit moral judgments
• Enhance summary quality while maintaining original intent

Innovation

• Preserves moral framing in AI news summaries
• Uses moral-laden words intentionally by journalists
• Combines automated and human evaluations for quality