RETSim: Resilient and Efficient Text Similarity
Not on the map. Why?
Abstract (arXiv)
This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and dataset deduplication tasks. We demonstrate that RETSim is significantly more robust and accurate than MinHash and neural text embeddings, achieving new state-of-the-art performance on dataset deduplication, adversarial text retrieval benchmarks, and spam clustering tasks. We also introduce the W4NT3D benchmark (Wiki-40B 4dversarial Near-T3xt Dataset) for evaluating multilingual, near-duplicate text retrieval capabilities under adversarial settings. RETSim and the W4NT3D benchmark are open-sourced under the MIT License at https://github.com/google/unisim.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 22 of its 32 references that are in the map. First posted on arXiv 28 Nov 2023.
Builds on
22 of 32 references.
References · 22
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2022A ConvNet for the 2020scited by 3,545
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
- 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
- 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
- 2021Deduplicating Training Data Makes Language Models Bettercited by 705
- 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 671
- 2022MTEB: Massive Text Embedding Benchmarkcited by 623
- 2020Language-agnostic BERT Sentence Embeddingcited by 621
- 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
- 2018Universal Sentence Encodercited by 485
10 more
- 2018Generating Natural Language Adversarial Examplescited by 422
- 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
- 2022The Stack: 3 TB of permissively licensed source codecited by 354
- 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
- 2022Deduplicating Training Data Mitigates Privacy Risks in Language Modelscited by 309
- 2019Multilingual Universal Sentence Encoder for Semantic Retrievalcited by 192
- 2022Transformer Quality in Linear Timecited by 189
- 2022Noise-Robust De-Duplication at Scalecited by 17
- 2023RETVec: Resilient and Efficient Text Vectorizercited by 3
- 2014Analysis of Phishing Attacks and Countermeasurescited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.