{"list":"other","total":52,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"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":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073},{"id":"1901.04085","title":"Passage Re-ranking with BERT","created":"2019-01-13","cited_by_count":645},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"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":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2107.05720","title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking","created":"2021-07-12","cited_by_count":286},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2402.01613","title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","created":"2024-02-02","cited_by_count":265},{"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":"2407.12883","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","created":"2024-07-16","cited_by_count":158},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147},{"id":"1901.08079","title":"A Question-Entailment Approach to Question Answering","created":"2019-01-23","cited_by_count":134},{"id":"2502.13595","title":"MMTEB: Massive Multilingual Text Embedding Benchmark","created":"2025-02-19","cited_by_count":125},{"id":"2212.05409","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","created":"2022-12-11","cited_by_count":102},{"id":"2406.14497","title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","created":"2024-06-20","cited_by_count":91},{"id":"2403.06789","title":"SPLADE-v3: New baselines for SPLADE","created":"2024-03-11","cited_by_count":72},{"id":"2403.15246","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","created":"2024-03-22","cited_by_count":69},{"id":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","cited_by_count":60},{"id":"2106.00882","title":"Efficient Passage Retrieval with Hashing for Open-domain Question Answering","created":"2021-06-02","cited_by_count":53},{"id":"2404.12096","title":"LongEmbed: Extending Embedding Models for Long Context Retrieval","created":"2024-04-18","cited_by_count":48},{"id":"2405.12497","title":"RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search","created":"2024-05-21","cited_by_count":48},{"id":"2210.09984","title":"Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages","created":"2022-10-18","cited_by_count":47},{"id":"2310.17609","title":"LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Dataset","created":"2023-10-26","cited_by_count":38},{"id":"2507.11412","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","created":"2025-07-15","cited_by_count":38},{"id":"2404.06347","title":"RAR-b: Reasoning as Retrieval Benchmark","created":"2024-04-09","cited_by_count":36},{"id":"1906.00424","title":"Plain English Summarization of Contracts","created":"2019-06-02","cited_by_count":28},{"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":"2505.14558","title":"R2MED: A Benchmark for Reasoning-Driven Medical Retrieval","created":"2025-05-20","cited_by_count":22},{"id":"2602.15547","title":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation","created":"2026-02-17","cited_by_count":22},{"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":"2104.09632","title":"Searching for Scientific Evidence in a Pandemic: An Overview of TREC-COVID","created":"2021-04-19","cited_by_count":19},{"id":"2503.04644","title":"IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval","created":"2025-03-06","cited_by_count":16},{"id":"2203.10232","title":"DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine","created":"2022-03-19","cited_by_count":15},{"id":"2305.19840","title":"BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language","created":"2023-05-31","cited_by_count":15},{"id":"2402.14151","title":"BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives","created":"2024-02-21","cited_by_count":15},{"id":"2405.20468","title":"MTEB-French: Resources for French Sentence Embedding Evaluation and Analysis","created":"2024-05-30","cited_by_count":6},{"id":"2412.06954","title":"CURE: A Dataset for Clinical Understanding & Retrieval Evaluation","created":"2024-12-09","cited_by_count":5},{"id":"2506.22141","title":"DAPFAM: A Domain-Aware Family-level Dataset to benchmark cross domain patent retrieval","created":"2025-06-27","cited_by_count":5},{"id":"2507.21500","title":"VN-MTEB: Vietnamese Massive Text Embedding Benchmark","created":"2025-07-29","cited_by_count":5},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5},{"id":"2409.07737","title":"Ruri: Japanese General Text Embeddings","created":"2024-09-12","cited_by_count":2},{"id":"2411.12056","title":"Benchmarking pre-trained text embedding models in aligning built asset information","created":"2024-11-18","cited_by_count":1}],"next_cursor":null}