{"list":"other","total":148,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"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":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"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":"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":"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":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2203.05794","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","created":"2022-03-11","cited_by_count":801},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"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":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476},{"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":"1705.02364","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","created":"2017-05-05","cited_by_count":432},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404},{"id":"1911.03891","title":"Social Bias Frames: Reasoning about Social and Power Implications of Language","created":"2019-11-10","cited_by_count":380},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","cited_by_count":361},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"id":"1506.06726","title":"Skip-Thought Vectors","created":"2015-06-22","cited_by_count":322},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2401.15391","title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","created":"2024-01-27","cited_by_count":257},{"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":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217},{"id":"2202.08904","title":"SGPT: GPT Sentence Embeddings for Semantic Search","created":"2022-02-17","cited_by_count":204},{"id":"2407.12883","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","created":"2024-07-16","cited_by_count":158},{"id":"2211.13308","title":"SciRepEval: A Multi-Format Benchmark for Scientific Document Representations","created":"2022-11-23","cited_by_count":129},{"id":"2502.13595","title":"MMTEB: Massive Multilingual Text Embedding Benchmark","created":"2025-02-19","cited_by_count":125},{"id":"1304.6480","title":"A Theoretical Analysis of NDCG Type Ranking Measures","created":"2013-04-24","cited_by_count":119},{"id":"2108.08787","title":"Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval","created":"2021-08-19","cited_by_count":119},{"id":"2408.10343","title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","created":"2024-08-19","cited_by_count":118},{"id":"2407.11005","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","created":"2024-06-25","cited_by_count":117},{"id":"2104.06979","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","created":"2021-04-14","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":"1703.02507","title":"Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features","created":"2017-03-07","cited_by_count":104},{"id":"2310.19923","title":"Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents","created":"2023-10-30","cited_by_count":104},{"id":"1809.02922","title":"Transforming Question Answering Datasets Into Natural Language Inference Datasets","created":"2018-09-09","cited_by_count":99},{"id":"2010.05338","title":"We Can Detect Your Bias: Predicting the Political Ideology of News Articles","created":"2020-10-11","cited_by_count":92},{"id":"2404.13781","title":"Evaluating Retrieval Quality in Retrieval-Augmented Generation","created":"2024-04-21","cited_by_count":90},{"id":"2407.15831","title":"NV-Retriever: Improving text embedding models with effective hard-negative mining","created":"2024-07-22","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":"2205.12404","title":"FLUTE: Figurative Language Understanding through Textual Explanations","created":"2022-05-24","cited_by_count":79},{"id":"2409.15700","title":"Making Text Embedders Few-Shot Learners","created":"2024-09-24","cited_by_count":79},{"id":"2004.03066","title":"Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition","created":"2020-04-07","cited_by_count":77},{"id":"2402.15449","title":"Repetition Improves Language Model Embeddings","created":"2024-02-23","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":"2204.12632","title":"Testing the Ability of Language Models to Interpret Figurative Language","created":"2022-04-26","cited_by_count":67},{"id":"2004.05080","title":"Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure","created":"2020-04-10","cited_by_count":60},{"id":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","cited_by_count":60},{"id":"2401.07078","title":"PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities","created":"2024-01-13","cited_by_count":59},{"id":"2412.04506","title":"Arctic-Embed 2.0: Multilingual Retrieval Without Compromise","created":"2024-12-03","cited_by_count":58},{"id":"1711.08792","title":"SPINE: SParse Interpretable Neural Embeddings","created":"2017-11-23","cited_by_count":55},{"id":"2402.07688","title":"CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge","created":"2024-02-12","cited_by_count":55},{"id":"1907.01041","title":"Natural Language Understanding with the Quora Question Pairs Dataset","created":"2019-07-01","cited_by_count":51},{"id":"2401.17043","title":"CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models","created":"2024-01-30","cited_by_count":50},{"id":"2407.18940","title":"LitSearch: A Retrieval Benchmark for Scientific Literature Search","created":"2024-07-10","cited_by_count":50},{"id":"2405.20204","title":"Jina CLIP: Your CLIP Model Is Also Your Text Retriever","created":"2024-05-30","cited_by_count":46},{"id":"2306.07934","title":"BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information","created":"2023-06-13","cited_by_count":44},{"id":"2402.16829","title":"GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning","created":"2024-02-26","cited_by_count":40},{"id":"2406.15187","title":"UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis","created":"2024-06-21","cited_by_count":40},{"id":"2410.10814","title":"Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free","created":"2024-10-14","cited_by_count":37},{"id":"2010.03450","title":"\"I'd rather just go to bed\": Understanding Indirect Answers","created":"2020-10-07","cited_by_count":36},{"id":"2307.11224","title":"Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models","created":"2023-07-20","cited_by_count":35},{"id":"2206.07023","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","created":"2022-06-14","cited_by_count":33},{"id":"2311.05296","title":"BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings","created":"2023-11-09","cited_by_count":32},{"id":"2407.01102","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":31},{"id":"2502.12378","title":"Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges","created":"2025-02-17","cited_by_count":31},{"id":"2402.09642","title":"Answer is All You Need: Instruction-following Text Embedding via Answering the Question","created":"2024-02-15","cited_by_count":27},{"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":"2408.16672","title":"Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever","created":"2024-08-29","cited_by_count":25},{"id":"2305.15077","title":"Contrastive Learning of Sentence Embeddings from Scratch","created":"2023-05-24","cited_by_count":24},{"id":"2109.06987","title":"NOPE: A Corpus of Naturally-Occurring Presuppositions in English","created":"2021-09-14","cited_by_count":23},{"id":"2408.00657","title":"Disentangling Dense Embeddings with Sparse Autoencoders","created":"2024-08-01","cited_by_count":23},{"id":"1711.00331","title":"Semantic Structure and Interpretability of Word Embeddings","created":"2017-11-01","cited_by_count":21},{"id":"2305.17746","title":"Whitening-based Contrastive Learning of Sentence Embeddings","created":"2023-05-28","cited_by_count":21},{"id":"2402.17016","title":"Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings","created":"2024-02-26","cited_by_count":21},{"id":"2305.14583","title":"Natural Language Decompositions of Implicit Content Enable Better Text Representations","created":"2023-05-23","cited_by_count":19},{"id":"2405.10138","title":"PL-MTEB: Polish Massive Text Embedding Benchmark","created":"2024-05-16","cited_by_count":19},{"id":"2412.11556","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","created":"2024-12-16","cited_by_count":18},{"id":"2502.10990","title":"FinMTEB: Finance Massive Text Embedding Benchmark","created":"2025-02-16","cited_by_count":18},{"id":"2406.05654","title":"DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation","created":"2024-06-09","cited_by_count":16}],"next_cursor":"100"}