arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.13852cs.CLcs.AI
收藏

语言模型是否言行一致?检验LLM中编码的关于性别化语言改革的语言意识形态

Do language models practice what they preach? Examining language ideologies about gendered language reform encoded in LLMs

University of Toronto(多伦多大学)

Julia Watson, Sophia Lee, Barend Beekhuizen, Suzanne Stevenson

AI总结:

本研究通过英语性别化语言改革案例,发现LLM在语言使用中存在政治偏见和内部不一致性,揭示了其隐含的语言意识形态,并讨论了对价值对齐的影响。

摘要:

我们通过英语性别化语言改革(涉及congressperson/-woman/-man等角色名词和单数they)的案例研究,探讨LLM生成文本中的语言意识形态。首先,我们发现政治偏见:当被要求使用“正确”或“自然”的语言时,LLM的语言使用与被要求遵循保守派(相对于进步派)价值观时最为相似。这表明LLM的元语言偏好如何在看似非政治的语境中,隐含地传达特定政治群体的语言意识形态。其次,我们发现LLM表现出内部不一致:当提供更明确的元语言语境时,LLM更频繁地使用性别中立变体。这表明LLM生成文本中表达的语言意识形态可能发生变化,这可能出乎用户意料。我们讨论了这些发现对价值对齐的更广泛影响。

英文摘要:

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.

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。

↑