# PLAID SHIRTTT for Large-Scale Streaming Dense Retrieval

arXiv: https://arxiv.org/abs/2405.00975 · HTML: https://mlsanity.com/paper/2405.00975/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 2 May 2024.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [Deeper Text Understanding for IR with Contextual Neural Language Modeling](https://mlsanity.com/paper/1905.09217/) (2019)
- [PLAID: An Efficient Engine for Late Interaction Retrieval](https://mlsanity.com/paper/2205.09707/) (2022)
- [Neural Approaches to Multilingual Information Retrieval](https://mlsanity.com/paper/2209.01335/) (2022)
- [Overview of the TREC 2023 NeuCLIR Track](https://mlsanity.com/paper/2404.08071/) (2024)
- [Overview of the TREC 2022 NeuCLIR Track](https://mlsanity.com/paper/2304.12367/) (2023)

## Built on by (most cited first, 3 of 3)

- [Evaluating Large Language Models for Cross-Lingual Retrieval](https://mlsanity.com/paper/2509.14749/) (2025)
- [MURR: Model Updating with Regularized Replay for Searching a Document Stream](https://mlsanity.com/paper/2504.10250/) (2025)
- [ICICLE: Expanding Retrieval with In-Context Documents](https://mlsanity.com/paper/2605.26902/) (2026)

## Abstract (arXiv)

PLAID, an efficient implementation of the ColBERT late interaction bi-encoder using pretrained language models for ranking, consistently achieves state-of-the-art performance in monolingual, cross-language, and multilingual retrieval. PLAID differs from ColBERT by assigning terms to clusters and representing those terms as cluster centroids plus compressed residual vectors. While PLAID is effective in batch experiments, its performance degrades in streaming settings where documents arrive over time because representations of new tokens may be poorly modeled by the earlier tokens used to select cluster centroids. PLAID Streaming Hierarchical Indexing that Runs on Terabytes of Temporal Text (PLAID SHIRTTT) addresses this concern using multi-phase incremental indexing based on hierarchical sharding. Experiments on ClueWeb09 and the multilingual NeuCLIR collection demonstrate the effectiveness of this approach both for the largest collection indexed to date by the ColBERT architecture and in the multilingual setting, respectively.