LLMs隐含保守语言倾向，且表现前后不一。
Do language models practice what they preach? Examining language ideologies about gendered language reform encoded in LLMs
- 通过角色词与单数they测试，发现模型偏好保守语用
- 提供明确语境时，中性用法使用率显著提升
- 揭示大模型语言意识形态的隐蔽性与不一致性
我们通过英语性别化语言改革（如congressperson/-woman/-man和singular they）的案例研究，探讨大模型生成文本中的语言意识形态。首先发现政治偏向：当要求使用“正确”或“自然”的语言时，模型表现更接近保守价值观，而非进步价值观，表明大模型的元语言偏好可能在看似中立的语境中传达特定政治群体的语言观念。其次发现内部不一致：当提供更明确的元语言上下文时，模型更频繁使用性别中性表达，说明其语言意识形态可随提示变化，对用户而言可能出乎意料。这些发现对大模型的价值对齐具有深远影响。
原文摘要 · Abstract (English)
We study language ideologies in text produced by LLMs through a case study on English gendered language reform (related to role nouns like congressperson/-woman/-man, and singular they). First, we find political bias: when asked to use language that is "correct" or "natural", LLMs use language most similarly to when asked to align with conservative (vs. progressive) values. This shows how LLMs' metalinguistic preferences can implicitly communicate the language ideologies of a particular political group, even in seemingly non-political contexts. Second, we find LLMs exhibit internal inconsistency: LLMs use gender-neutral variants more often when more explicit metalinguistic context is provided. This shows how the language ideologies expressed in text produced by LLMs can vary, which may be unexpected to users. We discuss the broader implications of these findings for value alignment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。