Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors

Abstract

Sparse annotation poses persistent challenges to training dense retrieval models; for example, it distorts the training signal when unlabeled relevant documents are used spuriously as negatives in contrastive learning. To alleviate this problem, we introduce evidence-based label smoothing, a novel, computationally efficient method that prevents penalizing the model for assigning high relevance to false negatives. To compute the target relevance distribution over candidate documents within the ranking context of a given query, we assign a non-zero relevance probability to those candidates most similar to the ground truth based on the degree of their similarity to the ground-truth document(s). To estimate relevance we leverage an improved similarity metric based on reciprocal nearest neighbors, which can also be used independently to rerank candidates in post-processing. Through extensive experiments on two large-scale ad hoc text retrieval datasets, we demonstrate that reciprocal near

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyzerveas2023enhancing

Related papers

• Learning To Retrieve: How To Train A Dense Retrieval Model Effectively And Efficiently (2020)0.00
• Bixse: Improving Dense Retrieval Via Probabilistic Graded Relevance Distillation (2025)0.00
• CODER: An Efficient Framework For Improving Retrieval Through Contextual Document Embedding Reranking (2021)7.16
• Optimizing Dense Retrieval Model Training With Hard Negatives (2021)16.34
• Approximate Nearest Neighbor Negative Contrastive Learning For Dense Text Retrieval (2020)0.00
• Pseudo-relevance Feedback For Multiple Representation Dense Retrieval (2021)12.93
• Pairdistill: Pairwise Relevance Distillation For Dense Retrieval (2024)7.24
• Learning More From Less: Towards Strengthening Weak Supervision For Ad-hoc Retrieval (2019)5.84