{"list":"other","total":98,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"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":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"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":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"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":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"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":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"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":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"2003.04807","title":"Efficient Intent Detection with Dual Sentence Encoders","created":"2020-03-10","cited_by_count":433},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"1908.11828","title":"PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification","created":"2019-08-30","cited_by_count":264},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"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":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233},{"id":"1704.05179","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","created":"2017-04-18","cited_by_count":225},{"id":"2402.13446","title":"Large Language Models for Data Annotation and Synthesis: A Survey","created":"2024-02-21","cited_by_count":205},{"id":"2102.07033","title":"PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them","created":"2021-02-13","cited_by_count":200},{"id":"2004.10706","title":"CORD-19: The COVID-19 Open Research Dataset","created":"2020-04-22","cited_by_count":180},{"id":"1911.04944","title":"CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB","created":"2019-11-10","cited_by_count":177},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177},{"id":"2008.09335","title":"MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark","created":"2020-08-21","cited_by_count":158},{"id":"2110.01799","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","created":"2021-10-05","cited_by_count":148},{"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":"2108.08787","title":"Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval","created":"2021-08-19","cited_by_count":119},{"id":"2108.13897","title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset","created":"2021-08-31","cited_by_count":116},{"id":"2412.19048","title":"Jasper and Stella: distillation of SOTA embedding models","created":"2024-12-26","cited_by_count":112},{"id":"1711.05073","title":"DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications","created":"2017-11-14","cited_by_count":110},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97},{"id":"2503.07891","title":"Gemini Embedding: Generalizable Embeddings from Gemini","created":"2025-03-10","cited_by_count":94},{"id":"2305.06849","title":"WebCPM: Interactive Web Search for Chinese Long-form Question Answering","created":"2023-05-11","cited_by_count":93},{"id":"2010.05444","title":"OCNLI: Original Chinese Natural Language Inference","created":"2020-10-12","cited_by_count":86},{"id":"1810.07366","title":"A Span-Extraction Dataset for Chinese Machine Reading Comprehension","created":"2018-10-17","cited_by_count":84},{"id":"2403.20327","title":"Gecko: Versatile Text Embeddings Distilled from Large Language Models","created":"2024-03-29","cited_by_count":83},{"id":"2409.15700","title":"Making Text Embedders Few-Shot Learners","created":"2024-09-24","cited_by_count":79},{"id":"2404.10981","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","created":"2024-04-17","cited_by_count":77},{"id":"1506.05865","title":"LCSTS: A Large Scale Chinese Short Text Summarization Dataset","created":"2015-06-19","cited_by_count":65},{"id":"2206.06588","title":"Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search","created":"2022-06-14","cited_by_count":65},{"id":"1908.06605","title":"Long and Diverse Text Generation with Planning-based Hierarchical Variational Model","created":"2019-08-19","cited_by_count":62},{"id":"2304.03679","title":"T2Ranking: A large-scale Chinese Benchmark for Passage Ranking","created":"2023-04-07","cited_by_count":60},{"id":"1806.00920","title":"DRCD: a Chinese Machine Reading Comprehension Dataset","created":"2018-06-04","cited_by_count":57},{"id":"2104.08727","title":"GooAQ: Open Question Answering with Diverse Answer Types","created":"2021-04-18","cited_by_count":53},{"id":"2404.07221","title":"Improving Retrieval for RAG based Question Answering Models on Financial Documents","created":"2024-03-23","cited_by_count":49},{"id":"2205.12654","title":"Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages","created":"2022-05-25","cited_by_count":48},{"id":"2104.06893","title":"I Wish I Would Have Loved This One, But I Didn't -- A Multilingual Dataset for Counterfactual Detection in Product Reviews","created":"2021-04-14","cited_by_count":45},{"id":"2209.05034","title":"CSL: A Large-scale Chinese Scientific Literature Dataset","created":"2022-09-12","cited_by_count":45},{"id":"2311.13534","title":"LM-Cocktail: Resilient Tuning of Language Models via Model Merging","created":"2023-11-22","cited_by_count":44},{"id":"2104.07081","title":"TWEAC: Transformer with Extendable QA Agent Classifiers","created":"2021-04-14","cited_by_count":37},{"id":"2206.11863","title":"CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking","created":"2022-06-06","cited_by_count":37},{"id":"2210.16773","title":"An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks","created":"2022-10-30","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":"1911.08962","title":"CAIL2019-SCM: A Dataset of Similar Case Matching in Legal Domain","created":"2019-11-20","cited_by_count":30},{"id":"2203.03367","title":"Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval","created":"2022-03-07","cited_by_count":27},{"id":"2311.05800","title":"Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval","created":"2023-11-10","cited_by_count":24},{"id":"2410.10293","title":"FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG","created":"2024-10-14","cited_by_count":18},{"id":"2305.14994","title":"RefGPT: Dialogue Generation of GPT, by GPT, and for GPT","created":"2023-05-24","cited_by_count":15},{"id":"2207.01426","title":"Dynamic Contrastive Distillation for Image-Text Retrieval","created":"2022-07-04","cited_by_count":14},{"id":"2004.11142","title":"DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications","created":"2020-04-23","cited_by_count":13},{"id":"2412.13102","title":"AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark","created":"2024-12-17","cited_by_count":12},{"id":"2506.03483","title":"APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training","created":"2025-06-04","cited_by_count":12},{"id":"2405.06932","title":"Piccolo2: General Text Embedding with Multi-task Hybrid Loss Training","created":"2024-05-11","cited_by_count":10},{"id":"2410.11315","title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","created":"2024-10-15","cited_by_count":9},{"id":"2506.06313","title":"Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering","created":"2025-05-26","cited_by_count":7},{"id":"2202.10974","title":"The Winning Solution to the iFLYTEK Challenge 2021 Cultivated Land Extraction from High-Resolution Remote Sensing Image","created":"2022-02-22","cited_by_count":3}],"next_cursor":null}