Metraipolis › archive › dc_3f0fba09d7fd

How Robust Is Multimodal Claim Verification to LLM Rewriting? — arXiv:2610.02841

Source
arXiv
Original
https://arxiv.org/abs/2610.02841
License (as archived)
CC0-1.0
Archived
2026-10-05T22:51:36.320Z
SHA-256 of the archived text
01b30fb493746a21f6f8a06d89fc2a65795b1767bc0e6436ceeb6970f4df6b4f
Stable URL of this page
https://metraipolis.com/documento/dc_3f0fba09d7fd

How to cite

How Robust Is Multimodal Claim Verification to LLM Rewriting? — arXiv:2610.02841 — arXiv, https://arxiv.org/abs/2610.02841 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f0fba09d7fd (Metraipolis archive dc_3f0fba09d7fd, sha256 01b30fb493746a21f6f8a06d89fc2a65795b1767bc0e6436ceeb6970f4df6b4f)
BibTeX
@misc{dc3f0fba09d7fd,
  title = {How Robust Is Multimodal Claim Verification to LLM Rewriting? — arXiv:2610.02841},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02841},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f0fba09d7fd; sha256 01b30fb493746a21f6f8a06d89fc2a65795b1767bc0e6436ceeb6970f4df6b4f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02841. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLMs are known to introduce stylistic changes into generated text, yet how these stylistic shifts affect model decisions on scientific tasks remains underexplored. In this paper, we focus on multimodal claim verification, where the goal is to determine whether a textual claim is grounded in a given piece of evidence. We apply two rewriting strategies: natural rewriting, which simulates how researchers routinely use LLMs to polish academic text, and controlled injection, which inserts a single LLM-associated word to isolate the effect of vocabulary choice. We evaluate 11 open-weight models spanning five VLM families and ranging from 2B to 38B parameters. We find that models are robust to these modifications: most show no significant drop in accuracy, and compared to prior work on review-score manipulation, verification appears far more stable. However, consistent probability shifts do occur. Hedging-oriented conditions produce significant shifts across nearly all models, while boosting conditions show a weaker effect and general polishing conditions (e.g., grammar correction, fluency improvement) have little effect.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.02841 — 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 2026-10-05T22:46:10.553Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).