Metraipolis › archive › dc_54965042cfec

Misinformation Without Triggers: From Factual Answers to Downstream Decisions — arXiv:2610.02886

Source: arXiv
Original: https://arxiv.org/abs/2610.02886
License (as archived): CC0-1.0
Archived: 2026-10-05T22:50:20.121Z
SHA-256 of the archived text: 0c1556ca6a0d9b48d1cb812643a85e9fae912ac606933675d7de4ef43096b11d
Stable URL of this page: https://metraipolis.com/documento/dc_54965042cfec

How to cite

Misinformation Without Triggers: From Factual Answers to Downstream Decisions — arXiv:2610.02886 — arXiv, https://arxiv.org/abs/2610.02886 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_54965042cfec (Metraipolis archive dc_54965042cfec, sha256 0c1556ca6a0d9b48d1cb812643a85e9fae912ac606933675d7de4ef43096b11d)

BibTeX

@misc{dc54965042cfec,
  title = {Misinformation Without Triggers: From Factual Answers to Downstream Decisions — arXiv:2610.02886},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02886},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_54965042cfec; sha256 0c1556ca6a0d9b48d1cb812643a85e9fae912ac606933675d7de4ef43096b11d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02886. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language models learn from web documents, some of them false, and false content can reach a model's answer to a factual question and the summaries and decisions that use it. Most data-poisoning studies add a trigger to the training data and activate it in the prompt. False documents can also change factual responses without any trigger, but we do not know whether the direct answer predicts the decision. In this work, we follow false content past the answer and find an \emph{audit gap} between what a direct probe reports and what the model then does, comparing false training with matched truthful controls in a controlled decision task, \emph{Guess the Capital}, where a fixed decoder turns factual answers into a scored card choice, and on a misleading claim from Facebook posts about the 2019--20 Australian bushfires. Across eight models at dose 1,000, direct injected-choice rates reach 95.8--100\%, while injected game choices increase by 1.7--14.4 percentage points over matched truthful training. The gap runs the other way too. Facts that pass the direct probe still push decisions toward the injected answer, and game accuracy drops further than those choices explain. Truthful correction brings the fact back but not the decisions built on it. We then look into the real-world bushfire case, models trained on the false posts say that people were arrested for arson even when they lose the inflated count, and in a count-by-wording factorial the misleading arrest wording produces arrest assertions even when the training count stays at 24. In simpler terms, \textbf{a correct factual answer does not guarantee a correct decision, and losing the injected number does not remove the misleading story}.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02886 — 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 2026-10-05T22:45:55.807Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).