# Improving Out-of-Distribution Generalization of Neural Rerankers with Contextualized Late Interaction

arXiv: https://arxiv.org/abs/2302.06589 · HTML: https://mlsanity.com/paper/2302.06589/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 15 of 15)

- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [A Deep Relevance Matching Model for Ad-hoc Retrieval](https://mlsanity.com/paper/1711.08611/) (2017)
- [COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List](https://mlsanity.com/paper/2104.07186/) (2021)
- [SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval](https://mlsanity.com/paper/2207.02578/) (2022)
- [End-to-End Neural Ad-hoc Ranking with Kernel Pooling](https://mlsanity.com/paper/1706.06613/) (2017)
- [CEDR: Contextualized Embeddings for Document Ranking](https://mlsanity.com/paper/1904.07094/) (2019)
- [Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline](https://mlsanity.com/paper/2101.08751/) (2021)
- [Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?](https://mlsanity.com/paper/2110.06918/) (2021)
- [PACRR: A Position-Aware Neural IR Model for Relevance Matching](https://mlsanity.com/paper/1704.03940/) (2017)
- [CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval](https://mlsanity.com/paper/2211.10411/) (2022)

## Built on by (most cited first, 1 of 1)

- [Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?](https://mlsanity.com/paper/2311.09175/) (2023)

## Abstract (arXiv)

Recent progress in information retrieval finds that embedding query and document representation into multi-vector yields a robust bi-encoder retriever on out-of-distribution datasets. In this paper, we explore whether late interaction, the simplest form of multi-vector, is also helpful to neural rerankers that only use the [CLS] vector to compute the similarity score. Although intuitively, the attention mechanism of rerankers at the previous layers already gathers the token-level information, we find adding late interaction still brings an extra 5% improvement in average on out-of-distribution datasets, with little increase in latency and no degradation in in-domain effectiveness. Through extensive experiments and analysis, we show that the finding is consistent across different model sizes and first-stage retrievers of diverse natures and that the improvement is more prominent on longer queries.