零样本跨语言重排序：面向低资源语言的大语言模型
Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages
AI总结：
本研究探索大语言模型在非洲低资源语言跨语言检索中的零样本重排序能力，比较专有与开源模型，发现跨语言重排序可媲美单语重排序。
摘要：
大语言模型（LLMs）在各种文档重排序任务中展现出了令人瞩目的零样本能力。尽管已有成功实施，但现有文献中关于其在低资源语言中有效性的研究仍存在空白。为填补这一空白，我们研究了LLMs如何在非洲语言的跨语言信息检索（CLIR）系统中充当重排序器。我们的实现覆盖英语和四种非洲语言（豪萨语、索马里语、斯瓦希里语和约鲁巴语），并考察了以英语为查询、非洲语言为段落的跨语言重排序。此外，我们分析并比较了使用查询和文档翻译的单语重排序的有效性。我们还评估了LLMs在利用自身生成的翻译时的有效性。为了了解多个LLMs的有效性，我们的研究聚焦于专有模型RankGPT-4和RankGPT-3.5，以及开源模型RankZephyr。虽然重排序在英语中仍然最为有效，但我们的结果表明，根据LLM的多语言能力，跨语言重排序可能与非洲语言中的重排序具有竞争力。
英文摘要：
Large language models (LLMs) have shown impressive zero-shot capabilities in various document reranking tasks. Despite their successful implementations, there is still a gap in existing literature on their effectiveness in low-resource languages. To address this gap, we investigate how LLMs function as rerankers in cross-lingual information retrieval (CLIR) systems for African languages. Our implementation covers English and four African languages (Hausa, Somali, Swahili, and Yoruba) and we examine cross-lingual reranking with queries in English and passages in the African languages. Additionally, we analyze and compare the effectiveness of monolingual reranking using both query and document translations. We also evaluate the effectiveness of LLMs when leveraging their own generated translations. To get a grasp of the effectiveness of multiple LLMs, our study focuses on the proprietary models RankGPT-4 and RankGPT-3.5, along with the open-source model, RankZephyr. While reranking remains most effective in English, our results reveal that cross-lingual reranking may be competitive with reranking in African languages depending on the multilingual capability of the LLM.
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。
