多语言语言模型中的知识与参照是否具有跨语言一致性？
Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?
AI总结：
该研究针对多语言模型事实性知识的跨语言一致性展开分析评估，借助可解释性方法揭示其影响因素，验证了语码转换训练等策略及激活修补方法对提升一致性的效用。
摘要：
在评估跨语言迁移能力、维持模型知识跨语言的事实性以及保障语言模型性能均等性时，应当考虑跨语言一致性。因此，我们聚焦于对事实性知识的跨语言一致性进行分析、评估与阐释。为推进研究，我们借助传达相同跨语言知识的语码混合共指陈述，检验了多个预训练模型与微调模型。我们利用可解释性方法分析模型在跨语言语境下的行为，发现多语言模型的一致性水平存在差异，且受语系、语言因素、书写系统以及特定层的跨语言一致性瓶颈影响。语码转换训练与跨语言词对齐目标取得了最为可观的效果，凸显了跨语言对齐监督与语码转换策略对提升多语言性能和跨语言一致性的价值。此外，实验结果表明，通过激活修补在测试阶段校准一致性具有良好前景。
英文摘要：
Cross-lingual consistency should be considered to assess cross-lingual transferability, maintain the factuality of the model knowledge across languages, and preserve the parity of language model performance. We are thus interested in analyzing, evaluating, and interpreting cross-lingual consistency for factual knowledge. To facilitate our study, we examine multiple pretrained models and tuned models with code-mixed coreferential statements that convey identical knowledge across languages. Interpretability approaches are leveraged to analyze the behavior of a model in cross-lingual contexts, showing different levels of consistency in multilingual models, subject to language families, linguistic factors, scripts, and a bottleneck in cross-lingual consistency on a particular layer. Code-switching training and cross-lingual word alignment objectives show the most promising results, emphasizing the worthiness of cross-lingual alignment supervision and code-switching strategies for both multilingual performance and cross-lingual consistency enhancement. In addition, experimental results suggest promising result for calibrating consistency in the test time via activation patching.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
