Towards Robust Ranker for Text Retrieval
원문 초록
A ranker plays an indispensable role in the de facto 'retrieval & rerank' pipeline, but its training still lags behind -- learning from moderate negatives or/and serving as an auxiliary module for a retriever. In this work, we first identify two major barriers to a robust ranker, i.e., inherent label noises caused by a well-trained retriever and non-ideal negatives sampled for a high-capable ranker. Thereby, we propose multiple retrievers as negative generators improve the ranker's robustness, where i) involving extensive out-of-distribution label noises renders the ranker against each noise distribution, and ii) diverse hard negatives from a joint distribution are relatively close to the ranker's negative distribution, leading to more challenging thus effective training. To evaluate our robust ranker (dubbed R$^2$anker), we conduct experiments in various settings on the popular passage retrieval benchmark, including BM25-reranking, full-ranking, retriever distillation, etc. The empirical results verify the new state-of-the-art effectiveness of our model.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
JointRank: Rank Large Set with Single Pass
Tree-Based Text Retrieval via Hierarchical Clustering in RAGFrameworks: Application on Taiwanese Regulations
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning
MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling
Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
GLAP: General contrastive audio-text pretraining across domains and languages
토론
이 논문과 연결된 포럼 글이 아직 없습니다.