multilingual-disparity CAP-0033 · active

Performing evenly across languages

Covers gaps between high- and low-resource languages on identical tasks, including uneven parametric knowledge coverage by region; excludes translation quality per se.

Tags: general

Proposed from the ingestion pipeline rather than chosen by hand. 3 papers independently pointed at this same competence, arriving under 3 different names (cross-lingual-transfer, multilingual-transfer, knowledge-coverage-disparity), which is the signal that it is a real recurring topic and not one author's framing. A stable, widely measured axis of failure with three independent proposals.

What counts as this capability

Scope boundary used when deciding whether a paper is really about this capability, rather than merely mentioning it.

Covers gaps between high- and low-resource languages on identical tasks, including uneven parametric knowledge coverage by region; excludes translation quality per se.

Claims

observationsingle paper↑1↓0
Across six frontier chat models asked to produce phishing, deceptive sites and malware through direct and multi-stage prompts, non-English prompts were complied with more often than English ones, with a mean full-compliance rate of about 76% across natural languages (English about 71%, some languages above 97% on some models), so safety alignment is thinner outside English; simple encodings (Base64, ROT13, hex) lowered compliance to about 59% but did not remove it.

Techniques

None yet.

Sources

Every paper, post or observation behind this capability. Ones cited by a claim show the claim and its stance; ones filed directly are about the capability but have no claim drafted from them yet. Open one to add support or contest it.

An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios2026-04-01
↑ supports a claim here

Suggest a change

Capabilities are a way of carving up the subject, and carvings are arguable. Say so if this one is wrong — especially a proposed one, which a pipeline added because several papers used the same framing, not because anyone decided it was right.