Towards Robust Ranker For Text Retrieval
2022 · Yucheng Zhou, Tao Shen, Xiubo Geng, et al.
Abstract
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 empi
Authors
(none)
Tags
Stats
Related papers
- Enhancing Retrieval Performance: An Ensemble Approach For Hard Negative Mining (2024)0.00
- Rank-k: Test-time Reasoning For Listwise Reranking (2025)0.00
- Optimizing Dense Retrieval Model Training With Hard Negatives (2021)16.34
- RRRA: Resampling And Reranking Through A Retriever Adapter (2025)0.00
- Refit: Relevance Feedback From A Reranker During Inference (2023)0.00
- Drowning In Documents: Consequences Of Scaling Reranker Inference (2024)0.00
- Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52
- Docrerank: Single-page Hard Negative Query Generation For Training Multi-modal RAG Rerankers (2025)3.58