דפוסי רמיזה בייצור: הסתאמות לקסיקלית, סמנטית ומבנית ביצירת מודלי שפה

תקציר מקורי באנגליתarXiv:2609.04484v1 Announce Type: cross 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 dati