{"list":"other","total":63,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2007.01852","title":"Language-agnostic BERT Sentence Embedding","created":"2020-07-03","cited_by_count":627},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472},{"id":"2004.07180","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","created":"2020-04-15","cited_by_count":430},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311},{"id":"2407.19669","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval","created":"2024-07-29","cited_by_count":236},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146},{"id":"2409.10173","title":"jina-embeddings-v3: Multilingual Embeddings With Task LoRA","created":"2024-09-16","cited_by_count":141},{"id":"2502.13595","title":"MMTEB: Massive Multilingual Text Embedding Benchmark","created":"2025-02-19","cited_by_count":125},{"id":"2108.13897","title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset","created":"2021-08-31","cited_by_count":116},{"id":"1912.09582","title":"BERTje: A Dutch BERT Model","created":"2019-12-19","cited_by_count":109},{"id":"2109.00904","title":"MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","created":"2021-09-02","cited_by_count":90},{"id":"2001.06286","title":"RobBERT: a Dutch RoBERTa-based Language Model","created":"2020-01-17","cited_by_count":88},{"id":"2407.15831","title":"NV-Retriever: Improving text embedding models with effective hard-negative mining","created":"2024-07-22","cited_by_count":84},{"id":"2301.01820","title":"InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval","created":"2023-01-04","cited_by_count":73},{"id":"2005.00033","title":"Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society","created":"2020-04-30","cited_by_count":72},{"id":"2405.05374","title":"Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models","created":"2024-05-08","cited_by_count":61},{"id":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51},{"id":"2010.06478","title":"XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization","created":"2020-10-13","cited_by_count":42},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40},{"id":"2408.04303","title":"Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP","created":"2024-08-08","cited_by_count":36},{"id":"2501.01028","title":"KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model","created":"2025-01-02","cited_by_count":36},{"id":"2406.13469","title":"Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks","created":"2024-06-19","cited_by_count":34},{"id":"2406.02396","title":"The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding","created":"2024-06-04","cited_by_count":26},{"id":"2101.05716","title":"SICKNL: A Dataset for Dutch Natural Language Inference","created":"2021-01-14","cited_by_count":20},{"id":"2305.15020","title":"An Efficient Multilingual Language Model Compression through Vocabulary Trimming","created":"2023-05-24","cited_by_count":20},{"id":"2408.12503","title":"The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design","created":"2024-08-22","cited_by_count":20},{"id":"2405.10138","title":"PL-MTEB: Polish Massive Text Embedding Benchmark","created":"2024-05-16","cited_by_count":19},{"id":"2305.19840","title":"BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language","created":"2023-05-31","cited_by_count":15},{"id":"1910.00896","title":"The merits of Universal Language Model Fine-tuning for Small Datasets -- a case with Dutch book reviews","created":"2019-10-02","cited_by_count":14},{"id":"2401.02709","title":"German Text Embedding Clustering Benchmark","created":"2024-01-05","cited_by_count":13},{"id":"2310.03477","title":"Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation","created":"2023-10-05","cited_by_count":11},{"id":"2410.18634","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","created":"2024-10-24","cited_by_count":11},{"id":"2502.03824","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","created":"2025-02-06","cited_by_count":11},{"id":"2411.01192","title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","created":"2024-11-02","cited_by_count":10},{"id":"2502.11571","title":"FaMTEB: Massive Text Embedding Benchmark in Persian Language","created":"2025-02-17","cited_by_count":10},{"id":"2502.20936","title":"WebFAQ: A Multilingual Collection of Natural Q&A Datasets for Dense Retrieval","created":"2025-02-28","cited_by_count":10},{"id":"2305.13026","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","created":"2023-05-22","cited_by_count":6},{"id":"2412.08329","title":"BEIR-NL: Zero-shot Information Retrieval Benchmark for the Dutch Language","created":"2024-12-11","cited_by_count":6},{"id":"2407.01091","title":"M2QA: Multi-domain Multilingual Question Answering","created":"2024-07-01","cited_by_count":5},{"id":"2412.07462","title":"Bilingual BSARD: Extending Statutory Article Retrieval to Dutch","created":"2024-12-10","cited_by_count":5},{"id":"2412.07633","title":"ChocoLlama: Lessons Learned From Teaching Llamas Dutch","created":"2024-12-10","cited_by_count":5},{"id":"2211.08192","title":"RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use","created":"2022-11-15","cited_by_count":2}],"next_cursor":null}