arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.27908cs.CLcs.AI
收藏

大语言模型安全中的极性盲性:对否定、反义词替换与对抗性框架的系统研究

Polarity Blindness in LLM Safety: A Systematic Study of Negation, Antonym Substitution, and Adversarial Framing

ELLIS Alicante(ELLIS阿利坎特);Czech Technical University in Prague(捷克布拉格理工大学);Universidad de Alicante(阿利坎特大学)

Diego Miguel Lozano, Erik Derner, Juan Antonio Pérez-Ortiz, Nuria Oliver

AI总结:

该研究系统探究LLM的极性盲性漏洞,发现其会破坏安全护栏,经多语言多模型基准测试证实该漏洞普遍存在,凸显语义鲁棒性的局限。

摘要:

否定仍是自然语言处理任务及模态下语言模型面临的持续挑战。我们表明,这一弱点可通过一种被称为极性盲性的结构漏洞破坏大语言模型(LLM)的安全护栏:即无法在极性改变的语言转换后识别有害意图。我们研究两种极性反转形式:语法否定与反义词替换,并以同义词替换作为极性保留的对照。我们进一步测试对抗性文本包装是否会放大这些失败。使用包含260个提示的基准测试,覆盖10个最先进的LLM和3种语言(英语、西班牙语、捷克语),按伤害潜力分层并经验证的0-5伤害量表评估,我们发现极性盲性影响了大多数被评估模型,最脆弱模型的平均伤害得分达4.12。该效应在类型学上不同的否定系统中持续存在,表明极性盲性反映了语义鲁棒性的更广泛局限,而非特定语言或语法的失败。

英文摘要:

Negation remains a persistent challenge for language models across NLP tasks and modalities. We show that this weakness can undermine LLM safety guardrails through a structural vulnerability we term polarity blindness: the failure to recognize harmful intent after polarity-altering linguistic transformations. We study two forms of polarity inversion: grammatical negation and antonym replacement, and use synonym replacement as a polarity-preserving control. We further test whether an adversarial textual wrapper amplifies these failures. Using a 260-prompt benchmark across 10 state-of-the-art LLMs and 3 languages (English, Spanish, Czech), stratified by harmfulness potential and evaluated on a validated 0-5 harm scale, we find that polarity blindness affects most evaluated models, with mean harm scores reaching 4.12 for the most vulnerable model. The effect persists across typologically differing negation systems, suggesting that polarity blindness reflects a broader limitation in semantic robustness rather than a language- or grammar-specific failure.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑