Contrastive fine-tuning often degrades strong dense retrievers, while combining cross-encoder listwise distillation with diverse synthetic queries consistently improves them.
Embedding-based Zero-shot Retrieval through Query Generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Passage retrieval addresses the problem of locating relevant passages, usually from a large corpus, given a query. In practice, lexical term-matching algorithms like BM25 are popular choices for retrieval owing to their efficiency. However, term-based matching algorithms often miss relevant passages that have no lexical overlap with the query and cannot be finetuned to downstream datasets. In this work, we consider the embedding-based two-tower architecture as our neural retrieval model. Since labeled data can be scarce and because neural retrieval models require vast amounts of data to train, we propose a novel method for generating synthetic training data for retrieval. Our system produces remarkable results, significantly outperforming BM25 on 5 out of 6 datasets tested, by an average of 2.45 points for Recall@1. In some cases, our model trained on synthetic data can even outperform the same model trained on real data
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data
Contrastive fine-tuning often degrades strong dense retrievers, while combining cross-encoder listwise distillation with diverse synthetic queries consistently improves them.