Despite the recent advancements in NLP with the advent of Large Language Models (LLMs), Entity Linking (EL) for historical texts remains challenging due to linguistic variation, noisy inputs, and evolving semantic conventions. Existing solutions either require substantial training data or rely on domain-specific rules that limit scalability. In this paper, we present MHEL-LLaMo (Multilingual Historical Entity Linking with Large Language MOdels), an unsupervised ensemble approach combining a Small Language Model (SLM) and an LLM. MHEL-LLaMo leverages a multilingual bi-encoder (BELA) for candidate retrieval and an instruction-tuned LLM for NIL prediction and candidate selection via prompt chaining. Our system uses SLM's confidence scores to discriminate between easy and hard samples, applying an LLM only for hard cases. This strategy reduces computational costs while preventing hallucinations on straightforward cases. We evaluate MHEL-LLaMo on four established benchmarks in six European languages (English, Finnish, French, German, Italian and Swedish) from the 19th and 20th centuries. Results demonstrate that MHEL-LLaMo outperforms state-of-the-art models without requiring fine-tuning, offering a scalable solution for low-resource historical EL. The implementation of MHEL-LLaMo is available on Github.

翻译：尽管大型语言模型的出现推动了自然语言处理领域的近期进展，但由于语言变异、噪声输入和语义规范的演变，历史文本的实体链接任务仍然充满挑战。现有解决方案要么需要大量训练数据，要么依赖特定领域规则，限制了可扩展性。本文提出MHEL-LLaMo（基于大型语言模型的多语言历史实体链接），这是一种结合小型语言模型与大型语言模型的无监督集成方法。MHEL-LLaMo利用多语言双编码器进行候选实体检索，并通过提示链技术使用指令调优的大型语言模型进行NIL预测与候选选择。本系统通过小型语言模型的置信度分数区分简单样本与困难样本，仅对困难案例调用大型语言模型。该策略在降低计算成本的同时，避免了简单案例中的幻觉生成问题。我们在涵盖六种欧洲语言（英语、芬兰语、法语、德语、意大利语和瑞典语）的四个19-20世纪基准数据集上评估MHEL-LLaMo。实验结果表明，MHEL-LLaMo在不需微调的情况下超越了现有最优模型，为低资源历史实体链接提供了可扩展的解决方案。MHEL-LLaMo的实现代码已在Github开源。