{"list":"other","total":60,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"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":"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":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"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":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"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":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"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":"2209.11755","title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","created":"2022-09-23","cited_by_count":235},{"id":"2102.07662","title":"Overview of the TREC 2020 deep learning track","created":"2021-02-15","cited_by_count":196},{"id":"2407.01449","title":"ColPali: Efficient Document Retrieval with Vision Language Models","created":"2024-06-27","cited_by_count":195},{"id":"2010.02666","title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation","created":"2020-10-06","cited_by_count":145},{"id":"2108.08787","title":"Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval","created":"2021-08-19","cited_by_count":119},{"id":"2205.04733","title":"From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective","created":"2022-05-10","cited_by_count":98},{"id":"2503.07891","title":"Gemini Embedding: Generalizable Embeddings from Gemini","created":"2025-03-10","cited_by_count":94},{"id":"2407.15831","title":"NV-Retriever: Improving text embedding models with effective hard-negative mining","created":"2024-07-22","cited_by_count":84},{"id":"2403.06789","title":"SPLADE-v3: New baselines for SPLADE","created":"2024-03-11","cited_by_count":72},{"id":"2104.12016","title":"Learning Passage Impacts for Inverted Indexes","created":"2021-04-24","cited_by_count":68},{"id":"2010.11386","title":"Distilling Dense Representations for Ranking using Tightly-Coupled Teachers","created":"2020-10-22","cited_by_count":52},{"id":"2004.05665","title":"Minimizing FLOPs to Learn Efficient Sparse Representations","created":"2020-04-12","cited_by_count":46},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34},{"id":"2507.05513","title":"Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model","created":"2025-07-07","cited_by_count":27},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26},{"id":"2404.18812","title":"Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations","created":"2024-04-29","cited_by_count":24},{"id":"2403.10407","title":"A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE","created":"2024-03-15","cited_by_count":18},{"id":"2402.17535","title":"Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control","created":"2024-02-27","cited_by_count":12},{"id":"2502.15526","title":"Scaling Sparse and Dense Retrieval in Decoder-Only LLMs","created":"2025-02-21","cited_by_count":12},{"id":"2304.12702","title":"A Static Pruning Study on Sparse Neural Retrievers","created":"2023-04-25","cited_by_count":11},{"id":"2112.05662","title":"Match Your Words! A Study of Lexical Matching in Neural Information Retrieval","created":"2021-12-10","cited_by_count":10},{"id":"2205.02870","title":"MS-Shift: An Analysis of MS MARCO Distribution Shifts on Neural Retrieval","created":"2022-05-05","cited_by_count":10},{"id":"2411.00786","title":"Interpret and Control Dense Retrieval with Sparse Latent Features","created":"2024-10-17","cited_by_count":10},{"id":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","cited_by_count":10},{"id":"2410.13230","title":"Starbucks-v2: Improved Training for 2D Matryoshka Embeddings","created":"2024-10-17","cited_by_count":7},{"id":"2411.17299","title":"2D Matryoshka Training for Information Retrieval","created":"2024-11-26","cited_by_count":6},{"id":"2408.04443","title":"Pairing Clustered Inverted Indexes with kNN Graphs for Fast Approximate Retrieval over Learned Sparse Representations","created":"2024-08-08","cited_by_count":5},{"id":"2306.02867","title":"Benchmarking Middle-Trained Language Models for Neural Search","created":"2023-06-05","cited_by_count":4},{"id":"2501.11628","title":"Investigating the Scalability of Approximate Sparse Retrieval Algorithms to Massive Datasets","created":"2025-01-20","cited_by_count":4},{"id":"2504.18151","title":"Leveraging Decoder Architectures for Learned Sparse Retrieval","created":"2025-04-25","cited_by_count":4},{"id":"2505.11388","title":"The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems","created":"2025-05-16","cited_by_count":4},{"id":"2302.14723","title":"Extending English IR methods to multi-lingual IR","created":"2023-02-28","cited_by_count":3},{"id":"2305.14499","title":"NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders","created":"2023-05-23","cited_by_count":2}],"next_cursor":null}