Metraipolis › archive › dc_fded582abc6d

When Generated Information Returns: Error Persistence in LLM-Mediated Information Ecosystems — arXiv:2610.33617

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.33617
License (as archived): CC0-1.0
Archived: 2026-10-27T07:57:11.448Z
SHA-256 of the archived text: 0ac2dd96431ddc3db0c28f3f72d5e4bff8a3f35f13fdef8996d883a8747311ab
Stable URL of this page: https://metraipolis.com/documento/dc_fded582abc6d

How to cite

When Generated Information Returns: Error Persistence in LLM-Mediated Information Ecosystems — arXiv:2610.33617 — arXiv (en), https://arxiv.org/abs/2610.33617 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fded582abc6d (Metraipolis archive dc_fded582abc6d, sha256 0ac2dd96431ddc3db0c28f3f72d5e4bff8a3f35f13fdef8996d883a8747311ab)

BibTeX

@misc{dcfded582abc6d,
  title = {When Generated Information Returns: Error Persistence in LLM-Mediated Information Ecosystems — arXiv:2610.33617},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33617},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fded582abc6d; sha256 0ac2dd96431ddc3db0c28f3f72d5e4bff8a3f35f13fdef8996d883a8747311ab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33617. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) increasingly produce online articles from material that later becomes input to other models. This circulation connects individual responses to the information available for subsequent generation. We study a consequential distinction: an article can avoid endorsing a false claim while preserving the concrete details that enable its reproduction. Our framework connects claim content, expressed stance, and downstream reuse to explain selective error persistence under a continuing supply of accurate and inaccurate information. We implement a controlled community writing process that varies whether published articles return as inputs, matching external supply, input capacity, and generation volume. Across twelve factual targets and four production models, recirculation increases the presence of complete false claims by 7.29 percentage points at the final round while reducing explicit endorsement by 8.33 points. Effects differ across facts and models. Paired interventions then abstract eligible error details within fixed histories while preserving correct content and the surrounding controversy. Error reproduction remains largely unchanged across the evaluation targets, while a development quotation target exhibits local reductions. These findings connect persistent errors to the information available throughout a writing process and motivate evaluation of both what models affirm and what their publications supply to future writers.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.33617 — 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 2026-10-27T07:55:30.648Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).