TY - DATA
T1 - News is More than a Collection of Facts: Moral Frame Preserving News Summarization - code
PY - 2025/07/30
AU - Enrico Liscio
AU - Michela Lorandi
AU - Pradeep K. Murukannaiah
UR - 
DO - 10.4121/7b387539-0f9b-4143-b960-76eeef8886ab.v1
KW - Large Language Models (LLMs)
KW - News summarization
KW - Morality
KW - Framing
N2 - <p>Code used to generate summaries that preserve the moral framing of the original news article. We leverage the zero-shot summarization ability of Large Language Models, shown to produce results on par with human-generated summaries. We compare three language models and five prompting methods. Leveraging the intuition that journalists intentionally use or report moral-laden words in the article text, we propose approaches that first identify moral-laden words in the article (e.g., through Chain-of-Thought or supervised classification) and then guide the language model in preserving such words in the summary.</p>
ER -