Media / Publication
October 07, 2025

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

This paper investigates whether AI-generated news summaries retain journalists’ moral framing: the value-laden wording that conveys implicit judgments about events and actors. Its proposed method preserves these morally charged terms more effectively than existing approaches without reducing overall summary quality.

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.

To continue reading please visit: https://openreview.net/forum?id=uzauWUW9u3

This open access article was published in the Proceedings of the Second Conference on Language Modeling (COLM 2025) on 7 October 2025.

Liscio, E., Lorandi, M., & Murukannaiah, P. K. (2025, August 26). News is More than a Collection of Facts: Moral Frame Preserving News Summarization. Second Conference on Language Modeling. https://openreview.net/forum?id=uzauWUW9u3

Keywords: LLMs, news, summarization, morality, framing