arXiv cs.CL· Abderrahmane Issam, Irene E. Winther, Stefan L. Frank·· 13 小时前AI 评分31
双语语言模型能捕捉二语阅读中的跨语言影响
Bilingual Language Models Capture Cross-Linguistic Influence in Second-Language Reading
AI 导读
双语语言模型在预测二语阅读时间时，与读者母语匹配的模型优于单语英文基线和母语不匹配的双语模型。研究基于12种母语背景读者的英语阅读眼动数据，这一预测优势集中在晚期眼动指标，受母语与二语书写系统重叠程度调节，并在中等水平读者中最为明显。
正文 · 原文
Abstract:While monolingual language model (LM) surprisal is widely established as a predictor of reading times, it cannot capture the non-native (L2) reading dynamics that are shaped by the reader's first language (L1). In this work, we investigate whether the 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. To isolate L1-specific transfer, we compare bilingual models trained on an L1 that matches the readers' L1 background to both a monolingual English baseline and bilingual models trained on other L1s. We demonstrate that 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, and that such influence is present in L2 reading behavior.
| Comments: | Under review |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.31620 [cs.CL] |
| (or arXiv:2610.31620v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31620 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Abderrahmane Issam [view email]
[v1]
Thu, 22 Oct 2026 17:42:06 UTC (420 KB)
来源：arXiv cs.CL · arxiv.org