Comparative Analysis of Listwise Reranking with Large Language Models in Limited-Resource Language Contexts
This work addresses improving text ranking for low-resource languages, offering incremental insights into cost-effective solutions.
The study evaluated large language models (LLMs) for listwise reranking in limited-resource African languages, finding that proprietary models like RankGPT3.5 significantly outperformed traditional baselines such as BM25-DT in metrics like nDCG@10 and MRR@100.
Large Language Models (LLMs) have demonstrated significant effectiveness across various NLP tasks, including text ranking. This study assesses the performance of large language models (LLMs) in listwise reranking for limited-resource African languages. We compare proprietary models RankGPT3.5, Rank4o-mini, RankGPTo1-mini and RankClaude-sonnet in cross-lingual contexts. Results indicate that these LLMs significantly outperform traditional baseline methods such as BM25-DT in most evaluation metrics, particularly in nDCG@10 and MRR@100. These findings highlight the potential of LLMs in enhancing reranking tasks for low-resource languages and offer insights into cost-effective solutions.