Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation

2026-09-03

AI Summary

本文研究语言模型生成中结构启动效应，通过控制实验发现语义一致性增强结构启动，并在不同句式中观察到启动量差异。

Abstract

This paper investigates structural priming in language model (LM) production, examining how preceding structural context influences sentence completion. While prior work has demonstrated priming effects in comprehension of structural alternations, it remained unclear whether these persist in production, where, when generating, an LM samples from many possible continuations at each step. We address this question through a series of controlled sentence-completion experiments on dative constructions. In line with prior work, we find that LMs are susceptible to structural priming, particularly in sentences that are semantically coherent. In terms of priming magnitude, we find that while there is a greater relative increase of double-object datives against our baselines, in line with inverse frequency effects, there is a larger absolute increase in prepositional-objects, the more frequently produced construction. Finally, we not only observe that structural priming is boosted by lexico-semantic coherence, but that structurally primed completions display greater levels of lexico-semantic repetition. Taken together, our evidence supports the view that structural priming in LMs operates across multiple levels of linguistic representation, facilitating, and facilitated by syntactic, lexical, and semantic alignment. Code: https://github.com/the-context-lab/primedproduction.

Problem

• structural priming
• language model
• sentence completion
• dative constructions
• lexico-semantic coherence

Innovation

• structural priming
• language model generation
• lexico-semantic coherence
• syntactic alignment