Bilingual Lexicon Induction (BLI) is a core task in multilingual NLP that still, to a large extent, relies on calculating cross-lingual word representations. Inspired by the global paradigm shift in NLP towards Large Language Models (LLMs), we examine the potential of the latest generation of LLMs for the development of bilingual lexicons. We ask the following research question: Is it possible to prompt and fine-tune multilingual LLMs (mLLMs) for BLI, and how does this approach compare against and complement current BLI approaches? To this end, we systematically study 1) zero-shot prompting for unsupervised BLI and 2) few-shot in-context prompting with a set of seed translation pairs, both without any LLM fine-tuning, as well as 3) standard BLI-oriented fine-tuning of smaller LLMs. We experiment with 18 open-source text-to-text mLLMs of different sizes (from 0.3B to 13B parameters) on two standard BLI benchmarks covering a range of typologically diverse languages. Our work is the first to demonstrate strong BLI capabilities of text-to-text mLLMs. The results reveal that few-shot prompting with in-context examples from nearest neighbours achieves the best performance, establishing new state-of-the-art BLI scores for many language pairs. We also conduct a series of in-depth analyses and ablation studies, providing more insights on BLI with (m)LLMs, also along with their limitations.

翻译：双语词典归纳（BLI）是多语言自然语言处理中的核心任务，目前仍主要依赖于跨语言词向量计算。受自然语言处理领域向大型语言模型（LLM）全局范式转变的启发，我们探究了最新一代LLM在构建双语词典方面的潜力。我们提出以下研究问题：能否通过提示工程和微调多语言LLM（mLLM）来实现BLI？该方法如何与现有BLI方法进行比较和互补？为此，我们系统研究了：1）面向无监督BLI的零样本提示策略；2）基于种子翻译对集的小样本上下文提示方法（两者均无需LLM微调）；3）面向BLI的标准小规模LLM微调。我们使用18个不同参数量（0.3B至13B）的开源文本到文本mLLM进行实验，在覆盖多种语言类型的两个标准BLI基准上开展评估。本工作首次证明文本到文本mLLM具备强大的BLI能力。结果表明，基于最近邻上下文示例的小样本提示方法取得了最佳性能，为众多语言对创建了新的BLI最优得分。我们还开展了一系列深度分析与消融实验，为（多语言）LLM在BLI任务中的应用提供了更多见解，同时揭示了其局限性。