arXiv cs.CL· Gabriel Lars Sabadin, Dr Nicola Harding, Sarah Kingston·· 13 小时前AI 评分47
伤害是行为性的，审核是词汇性的：语言与文化如何决定自动化安全系统保护谁、噤声谁
Harm Is Behavioural, Moderation Is Lexical: How Language and Culture Decide Whom Automated Safety Systems Protect and Whom They Silence
AI 导读
论文指出自动内容审核系统依据词汇和表层形式而非信息实际行为判定伤害，导致过度标记与保护不足同源。研究将证据归纳为七种失效模式，并在11种语言上测试5个开放系统（从关键词词表到两个现有多语言 guard 模型），发现55个系统-语言组合中有51个未达到母语者区分有害功能与无害形式的准确率。能力提升在9种语言中提高了区分度，但阿拉伯语和罗马化印地语仍接近随机水平，最优与最差服务语言间的差距随能力扩大。
正文 · 原文
Abstract:Content warning: this paper quotes slurs and hateful statements from published test suites; the racial slur among them is masked.
Automated systems decide at scale which messages are harmful, and they decide unevenly. Classifiers label African American English as offensive up to twice as often as other English, the accounts of prominent drag queens can score as more toxic than those of white nationalists, and safety behaviour that holds in English collapses in low-resource languages. We argue that over-flagging and under-protection share one cause: deciding harm from vocabulary and surface form rather than from what a message does. We organise the evidence into seven failure modes and argue, as testable hypotheses, that harmful behaviours (a request for secrecy, a demand for payment, an attempt to isolate someone) travel across languages better than the words that express them. We propose an evaluation protocol that makes the gap between the best- and worst-served language communities a headline result, and show that the naive gap is inflated under equal service and that its usual bootstrap interval is unreliable. Applied to five open systems in eleven languages, from a keyword lexicon to two current multilingual guard models, the protocol finds that none reaches native-speaker accuracy at separating harmful function from harmless form (51 of 55 system-language pairs fall short); that greater capability raises discrimination in nine languages while leaving Arabic and romanised Hindi near chance, so the gap between the best- and worst-served languages grows with capability; that one system both over-flags and under-protects the same language most; and that a language a system reads worst can look the most fairly treated when only false positives are reported.
| Comments: | 18 pages, 2 figures. Code, simulations and per-case outputs: this https URL |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.7; K.4.1 |
| Cite as: | arXiv:2610.31047 [cs.CL] |
| (or arXiv:2610.31047v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31047 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Gabriel Lars Sabadin [view email]
[v1]
Thu, 22 Oct 2026 10:24:17 UTC (146 KB)
来源：arXiv cs.CL · arxiv.org