arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.09886cs.CL

利用意大利语和英语中的关系从句附着歧义探究多语言Transformer的句法偏见

Investigating Syntactic Biases in Multilingual Transformers with RC Attachment Ambiguities in Italian and English

University of Utah(犹他大学)

Michael Kamerath, Aniello De Santo

AI总结:

本文以意英关系从句附着歧义为对象,探究单/多语言LLM的类人偏好及词汇因素调节作用,发现模型行为存在差异且普遍难以捕捉类人偏好,提出该歧义是跨语言研究LLM语言知识与偏见的理想基准。

摘要:

本文利用过往句子处理研究,探究单语和多语言LLM在面对意大利语和英语中的关系从句附着歧义示例时是否表现出类人偏好。此外,我们测试这些偏好是否可被词汇因素(主句中的动词/名词类型)调节,此类因素已被证明与句法和语义关系的细微约束相关。我们的结果总体展示了LLM行为在不同模型间的有趣差异,也揭示了这些模型在正确捕捉类人偏好方面的普遍不足。基于这些结果,我们认为关系从句附着是跨语言探究LLM语言知识与偏见的理想基准。

英文摘要:

This paper leverages past sentence processing studies to investigate whether monolingual and multilingual LLMs show human-like preferences when presented with examples of relative clause attachment ambiguities in Italian and English. Furthermore, we test whether these preferences can be modulated by lexical factors (the type of verb/noun in the matrix clause) which have been shown to be tied to subtle constraints on syntactic and semantic relations. Our results overall showcase how LLM behavior varies interestingly across models, but also general failings of these models in correctly capturing human-like preferences. In light of these results, we argue that RC attachment is the ideal benchmark for cross-linguistic investigations of LLMs' linguistic knowledge and biases.

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。

↑