arXiv cs.CL· Claire Bonial, Claire Benet Post, Laura Michaelis, Harish Tayyar Madabushi·· 13 小时前AI 评分31
大语言模型的语言能产性研究：模型会强制转换，但不会抢先排除
Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt
AI 导读
一项跨多种规模与架构模型的测试发现，更大模型能识别强制转换（coercion）情形下的构式能产性，即使涉及新词；但即便最大模型也无法复现抢先排除（preemption）这一保守策略，不会利用负面证据在竞争性语法选项间做选择。研究认为，强制转换因兼具意外性与语义动机而可被检测，抢先排除则缺乏此类信号——被回避的词-构式配对没有记录，只有实际产出的才有。
正文 · 原文
Abstract:Usage-based theories of grammar explain language users' ability to interpret and produce novel combinations of words through two complementary inferential strategies. In cases of coercion, a language user, when encountering a word that is mismatched to its grammatical context, reinterprets that word in a way that resolves the conflict. In cases of preemption, the user infers that an otherwise plausible structure is unavailable or dispreferred because it fails to occur in contexts where it would be expected. Large Language Models are also usage-based, in the sense that the structures of language are learned through exposure to vast amounts of text. Here, we test whether or not the opposing forces of coercion and preemption also encourage and constrain linguistic productivity in LLMs. We demonstrate across models of various sizes and architectures that larger models recognize constructional productivity in cases of coercion, even when these involve novel words. However, we also show that even the largest models do not replicate the conservative language strategy of preemption for novel words: in particular, they do not appear to draw on negative evidence when making choices among competing grammatical options. We conclude that coercion is detectable because it is both surprising and semantically motivated: when a word is mismatched to its syntactic context, the word's meaning can be adjusted to fit the context. Preemption has no such signature. There is no record of the lexeme-construction pairings that were avoided--only of those that were produced. This asymmetry helps to explain why models coerce (create mismatched sign combinations) but do not preempt (avoid unconventional yet semantically defensible ones).
| Comments: | 18 pages, 9 tables (including Appendix) |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2606.02953 [cs.CL] |
| (or arXiv:2606.02953v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.02953 arXiv-issued DOI via DataCite |
Submission history
From: Claire Bonial [view email]
[v1]
Mon, 1 Jun 2026 23:11:39 UTC (134 KB)
[v2]
Wed, 21 Oct 2026 14:11:54 UTC (100 KB)
来源：arXiv cs.CL · arxiv.org