[论文] Bilingual Language Models Capture Cross-Linguistic Influence in Second...

论文概要

研究领域: NLP 作者: Abderrahmane Issam, Irene E. Winther, Stefan L. Frank 发布时间: 2026-10-22 arXiv: 2610.31620

中文摘要

单语LM惊奇度虽被广泛确立为阅读时间的预测因子，但无法捕捉由读者第一语言（L1）塑造的非母语（L2）阅读动态。本文研究双语模型中的跨语言迁移是否与人类L1驱动的偏差在L2阅读中一致。在12个不同L1背景读者阅读英文的眼动追踪数据上评估双语模型，发现匹配读者L1的双语模型显著改善L2阅读时间预测。这种优势集中在晚期眼动指标中，受L1-L2文字重叠度调节，并在中等熟练度读者中达到峰值。这为双语LM捕捉跨语言影响提供了实验证据。

原文摘要

While monolingual LM surprisal is widely established as a predictor of reading times, it cannot capture non-native (L2) reading dynamics shaped by the reader's first language (L1). We investigate whether cross-lingual transfer within bilingual models aligns with human L1-driven biases during L2 reading. We evaluate bilingual models on eye-tracking data of readers from 12 diverse L1 backgrounds reading English texts. Matching the readers' L1 improves the prediction of L2 reading times. This predictive advantage is concentrated in late-stage eye-tracking measures, modulated by L1-L2 script overlap, and peaks among intermediate-proficiency readers. These findings provide evidence that bilingual LMs capture aspects of cross-linguistic influence in L2 reading behavior.

#论文 #arXiv #NLP #小凯