标题： 探究任务算术在零样本信息检索中的应用 显示英文标题

标题： Investigating Task Arithmetic for Zero-Shot Information Retrieval

摘要： 大型语言模型（LLMs）在多种自然语言处理任务（包括文档重排序）的零样本性能上表现出令人印象深刻的能力。然而，它们在未见过的任务和领域中的有效性会下降，这主要是由于词汇和单词分布的变化。在这篇论文中，我们研究了任务算术，这是一种通过简单的数学运算（如加法或减法）结合在不同任务或领域预训练的LLMs权重的技术，以适应检索模型而无需额外的微调。我们的方法能够将多样化的任务和领域知识综合到一个单一模型中，从而实现在不同检索上下文中的有效零样本适应。在公开可用的科学、生物医学和多语言数据集上的广泛实验表明，我们的方法在NDCG@10上提高了最先进的重排序性能最多18%，在P@10上提高了15%。除了这些经验上的收益外，我们的分析还提供了关于任务算术作为零样本学习和模型适应实用策略的优势和局限性的见解。我们将代码公开提供在https://github.com/DetectiveMB/Task-Arithmetic-for-ZS-IR。 显示英文摘要

摘要： Large Language Models (LLMs) have shown impressive zero-shot performance across a variety of Natural Language Processing tasks, including document re-ranking. However, their effectiveness degrades on unseen tasks and domains, largely due to shifts in vocabulary and word distributions. In this paper, we investigate Task Arithmetic, a technique that combines the weights of LLMs pre-trained on different tasks or domains via simple mathematical operations, such as addition or subtraction, to adapt retrieval models without requiring additional fine-tuning. Our method is able to synthesize diverse tasks and domain knowledge into a single model, enabling effective zero-shot adaptation in different retrieval contexts. Extensive experiments on publicly available scientific, biomedical, and multilingual datasets show that our method improves state-of-the-art re-ranking performance by up to 18% in NDCG@10 and 15% in P@10. In addition to these empirical gains, our analysis provides insights into the strengths and limitations of Task Arithmetic as a practical strategy for zero-shot learning and model adaptation. We make our code publicly available at https://github.com/DetectiveMB/Task-Arithmetic-for-ZS-IR.