Assessing generalization capability of text ranking models in Polish
원문 초록
Retrieval-augmented generation (RAG) is becoming an increasingly popular technique for integrating internal knowledge bases with large language models. In a typical RAG pipeline, three models are used, responsible for the retrieval, reranking, and generation stages. In this article, we focus on the reranking problem for the Polish language, examining the performance of rerankers and comparing their results with available retrieval models. We conduct a comprehensive evaluation of existing models and those trained by us, utilizing a benchmark of 41 diverse information retrieval tasks for the Polish language. The results of our experiments show that most models struggle with out-of-domain generalization. However, a combination of effective optimization method and a large training dataset allows for building rerankers that are both compact in size and capable of generalization. The best of our models establishes a new state-of-the-art for reranking in the Polish language, outperforming existing models with up to 30 times more parameters.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
JointRank: Rank Large Set with Single Pass
Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation
InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking
Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.