# Can Cross Encoders Produce Useful Sentence Embeddings?

arXiv: https://arxiv.org/abs/2502.03552 · HTML: https://mlsanity.com/paper/2502.03552/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [Condenser: a Pre-training Architecture for Dense Retrieval](https://mlsanity.com/paper/2104.08253/) (2021)
- [Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation](https://mlsanity.com/paper/2010.02666/) (2020)
- [Zero-Shot Entity Linking by Reading Entity Descriptions](https://mlsanity.com/paper/1906.07348/) (2019)
- [Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline](https://mlsanity.com/paper/2101.08751/) (2021)
- [ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval](https://mlsanity.com/paper/2205.09153/) (2022)
- [TwinBERT: Distilling Knowledge to Twin-Structured BERT Models for Efficient Retrieval](https://mlsanity.com/paper/2002.06275/) (2020)
- [Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization](https://mlsanity.com/paper/2210.12579/) (2022)
- [Shallow Cross-Encoders for Low-Latency Retrieval](https://mlsanity.com/paper/2403.20222/) (2024)

## Built on by (most cited first, 2 of 2)

- [Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning](https://mlsanity.com/paper/2506.08354/) (2025)
- [Cross-Attention Calibrated Deduplication for Retrieval-Augmented Generation System](https://mlsanity.com/paper/2607.24332/) (2026)

## Abstract (arXiv)

Cross encoders (CEs) are trained with sentence pairs to detect relatedness. As CEs require sentence pairs at inference, the prevailing view is that they can only be used as re-rankers in information retrieval pipelines. Dual encoders (DEs) are instead used to embed sentences, where sentence pairs are encoded by two separate encoders with shared weights at training, and a loss function that ensures the pair's embeddings lie close in vector space if the sentences are related. DEs however, require much larger datasets to train, and are less accurate than CEs. We report a curious finding that embeddings from earlier layers of CEs can in fact be used within an information retrieval pipeline. We show how to exploit CEs to distill a lighter-weight DE, with a 5.15x speedup in inference time.