Metraipolis › archive › dc_be723fcd745e

In the Guise of Correction: How Framing and Cultural Adaptation Erode LLM Safety on Real-World Criminal Cases — arXiv:2610.21789

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21789
License (as archived)
CC0-1.0
Archived
2026-10-16T09:28:49.070Z
SHA-256 of the archived text
99fa73d0e9a7c82008b73f7acfee4e4f8db5d90a9761eab4f2ff0b870aa69ea9
Stable URL of this page
https://metraipolis.com/documento/dc_be723fcd745e

How to cite

In the Guise of Correction: How Framing and Cultural Adaptation Erode LLM Safety on Real-World Criminal Cases — arXiv:2610.21789 — arXiv (en), https://arxiv.org/abs/2610.21789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be723fcd745e (Metraipolis archive dc_be723fcd745e, sha256 99fa73d0e9a7c82008b73f7acfee4e4f8db5d90a9761eab4f2ff0b870aa69ea9)
BibTeX
@misc{dcbe723fcd745e,
  title = {In the Guise of Correction: How Framing and Cultural Adaptation Erode LLM Safety on Real-World Criminal Cases — arXiv:2610.21789},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be723fcd745e; sha256 99fa73d0e9a7c82008b73f7acfee4e4f8db5d90a9761eab4f2ff0b870aa69ea9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing safety benchmarks rely largely on synthetic prompts with loosely grounded taxonomies and offer little focused analysis of severe crime categories. We introduce GUISE, a benchmark of criminal-assistance scenarios sourced from real-world cases and organised under a taxonomy from the UNODC International Classification of Crime for Statistical Purposes (ICCS). Each scenario is rendered under three linguistic framings and evaluated across five distinct cultures. Using our proposed two-tier evaluation framework, which judges both harmfulness and operational uplift, we find that: (i) framing alone drives unsafe compliance, with the mean unsafe compliance rate rising from 28.9% under direct requests to 66.4% under correction seeking (peaking at 97.3%; p < 0.05), as models correcting deliberately distorted details supply executable criminal steps; (ii) culturally adapted prompts elicit significantly more unsafe compliance than literal translations of the same requests in all four non-English languages (+7 to +18 points), a risk that translation-based benchmarks miss; and (iii) unsafe responses from the least-safe models carry strong Anglocentric registers, and the extent of this leakage increases monotonically with response harmfulness ($\rho$ = 0.46 to 0.63 across languages, all p < 0.001). GUISE offers a grounded resource and fine-grained diagnostics for strengthening refusal alignment across languages and cultures. We publish our code and data to facilitate future research.

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); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2610.21789 — 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 2026-10-16T08:44:18.000Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).