Metraipolis › archive › dc_96ec0bb27f44

Recognizing Is Not Reversing: A Controlled Inversion Test of Fact-Preserving News Framing — arXiv:2609.11769

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.11769
License (as archived): CC0-1.0
Archived: 2026-10-16T05:27:13.620Z
SHA-256 of the archived text: ad695ab6c0c07fdd865c810dc62e85676910bb15a41bed5a090f02aeed3c2f45
Stable URL of this page: https://metraipolis.com/documento/dc_96ec0bb27f44

How to cite

Recognizing Is Not Reversing: A Controlled Inversion Test of Fact-Preserving News Framing — arXiv:2609.11769 — arXiv (en), https://arxiv.org/abs/2609.11769 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96ec0bb27f44 (Metraipolis archive dc_96ec0bb27f44, sha256 ad695ab6c0c07fdd865c810dc62e85676910bb15a41bed5a090f02aeed3c2f45)

BibTeX

@misc{dc96ec0bb27f44,
  title = {Recognizing Is Not Reversing: A Controlled Inversion Test of Fact-Preserving News Framing — arXiv:2609.11769},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11769},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96ec0bb27f44; sha256 ad695ab6c0c07fdd865c810dc62e85676910bb15a41bed5a090f02aeed3c2f45},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11769. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly used to analyze and rewrite news, yet current framing studies mainly evaluate generation, detection, or whether rewritten text appears more neutral. They do not directly show whether a model can undo a known framing transformation while keeping the facts fixed. We introduce a controlled inversion test over three established textual realizations of framing: evaluative lexis, agency realization, and information salience. Across 60 news articles and three intervention strengths, this yields 540 paired variants with preserved atomic facts and recorded edits. Across Qwen, DeepSeek, and Kimi, factual preservation remains near 0.84, whereas intervention reversal is 0.044--0.068. Even when both framing type and direction are recognized correctly, pooled reversal reaches 0.071. These results reveal a clear separation between factual fidelity, framing recognition, and framing inversion: recognizing how an article is framed does not imply that the framing can be undone.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.11769 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:17:52.195Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).