Metraipolis › archive › dc_3963bb5477ea

A Plausible Explanation Is Enough to Mislead Multimodal Judges — arXiv:2610.22631

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.22631
License (as archived): CC0-1.0
Archived: 2026-10-19T08:42:53.400Z
SHA-256 of the archived text: abde3b774cb644ec0aebc3c7882e4501d97f490a724b889b4e160874ccc6144b
Stable URL of this page: https://metraipolis.com/documento/dc_3963bb5477ea

How to cite

A Plausible Explanation Is Enough to Mislead Multimodal Judges — arXiv:2610.22631 — arXiv (en), https://arxiv.org/abs/2610.22631 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3963bb5477ea (Metraipolis archive dc_3963bb5477ea, sha256 abde3b774cb644ec0aebc3c7882e4501d97f490a724b889b4e160874ccc6144b)

BibTeX

@misc{dc3963bb5477ea,
  title = {A Plausible Explanation Is Enough to Mislead Multimodal Judges — arXiv:2610.22631},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22631},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3963bb5477ea; sha256 abde3b774cb644ec0aebc3c7882e4501d97f490a724b889b4e160874ccc6144b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22631. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal large language models (MLLMs) increasingly serve as judges in training and evaluation pipelines, often assessing answers together with explanations. Although AI judges are sensitive to textual factors, it remains unclear whether ordinary plausible explanations can sway judgments requiring visual verification. We introduce JUPE, a visual-question-answering (VQA)-style benchmark that fixes answers while varying explanations. Across 14 MLLM judges, ordinary explanations that sound plausible mislead judges, with effects comparable on average to deliberately persuasive arguments. Plain justifications and chain-of-thought rationales reduce rejection of incorrect answers by 12.7 and 13.8 percentage points, respectively. We call this failure plausibility capture. Using signal detection theory, we find a significant mean shift in decision criterion toward acceptance, without a clear change in mean discriminability. Explanations sway judgments across domains, explanation generators, and judging protocols, while tested mitigations offer limited, model-dependent protection. Such shifts can inflate performance estimates when judges evaluate answers with explanations.

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/2610.22631 — 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 2026-10-19T08:39:10.116Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).