Metraipolis › archive › dc_3de6e48e5ebd
Social Pressure Breaks Majority Voting in LLM Safety Panels — arXiv:2608.04415
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04415
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:24:38.584Z
- SHA-256 of the archived text
714786379b9141d730ceec32f35d2faab615cc11ca5fab7899805f61eb00066e- Stable URL of this page
https://metraipolis.com/documento/dc_3de6e48e5ebd
How to cite
Social Pressure Breaks Majority Voting in LLM Safety Panels — arXiv:2608.04415 — arXiv (en), https://arxiv.org/abs/2608.04415 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3de6e48e5ebd (Metraipolis archive dc_3de6e48e5ebd, sha256 714786379b9141d730ceec32f35d2faab615cc11ca5fab7899805f61eb00066e)
BibTeX
@misc{dc3de6e48e5ebd,
title = {Social Pressure Breaks Majority Voting in LLM Safety Panels — arXiv:2608.04415},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04415},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3de6e48e5ebd; sha256 714786379b9141d730ceec32f35d2faab615cc11ca5fab7899805f61eb00066e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04415. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly used to detect unsafe content. A common approach is to combine judgments from a panel of models to correct individual mistakes, but this benefit may disappear when every model sees the same misleading context before voting. We study this risk in a controlled two-round experiment. Each model first judges an item alone, then judges it again after six simulated peers either assert the wrong label or abstain. We combine the final judgments by majority vote. Across six open-weight LLMs and six datasets, we find that the wrong-label peer message raises the average reviewer false-alarm rate from 56.5% under silent peers to 87.5%, and majority voting raises the panel false-alarm rate to 100%. Without an asserted label, the same panel outperforms its average member. The effect is strongly asymmetric: reviewers follow pushes toward "unsafe" far more than pushes toward "safe" (about 75% versus 17%), so the panel's false-alarm rate rises sharply while its harmful-miss rate changes little. The proprietary-model probe shows substantial variation across models. These results identify susceptibility to shared social cues as a failure mode of safety panels and provide a simple pre-deployment diagnostic. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.04415 — 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 2026-10-31T11:13:23.167Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).