{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"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":"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":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"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":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333},{"id":"2004.07347","title":"HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data","created":"2020-04-15","cited_by_count":264},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233},{"id":"2311.17136","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","created":"2023-11-28","cited_by_count":166},{"id":"2010.10439","title":"Open Question Answering over Tables and Text","created":"2020-10-20","cited_by_count":163},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"2211.14876","title":"Dense Text Retrieval based on Pretrained Language Models: A Survey","created":"2022-11-27","cited_by_count":136},{"id":"2204.10298","title":"DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings","created":"2022-04-21","cited_by_count":132},{"id":"2205.12035","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","created":"2022-05-24","cited_by_count":118},{"id":"2406.15319","title":"LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs","created":"2024-06-21","cited_by_count":108},{"id":"2211.09260","title":"Task-aware Retrieval with Instructions","created":"2022-11-16","cited_by_count":107},{"id":"2404.08189","title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","created":"2024-04-12","cited_by_count":93},{"id":"2207.02578","title":"SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval","created":"2022-07-06","cited_by_count":90},{"id":"2312.15503","title":"Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval","created":"2023-12-24","cited_by_count":78},{"id":"2103.12011","title":"Open Domain Question Answering over Tables via Dense Retrieval","created":"2021-03-22","cited_by_count":74},{"id":"2402.11690","title":"Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning","created":"2024-02-18","cited_by_count":73},{"id":"2005.11723","title":"Query Resolution for Conversational Search with Limited Supervision","created":"2020-05-24","cited_by_count":52},{"id":"2305.07288","title":"Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Table","created":"2023-05-12","cited_by_count":40},{"id":"2109.03381","title":"Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering","created":"2021-09-08","cited_by_count":39},{"id":"2204.14272","title":"End-to-end Spoken Conversational Question Answering: Task, Dataset and Model","created":"2022-04-29","cited_by_count":37},{"id":"2010.08923","title":"Towards Data Distillation for End-to-end Spoken Conversational Question Answering","created":"2020-10-18","cited_by_count":35},{"id":"2110.08417","title":"Open Domain Question Answering with A Unified Knowledge Interface","created":"2021-10-16","cited_by_count":32},{"id":"2010.11067","title":"Knowledge Distillation for Improved Accuracy in Spoken Question Answering","created":"2020-10-21","cited_by_count":31},{"id":"2106.02182","title":"Self-supervised Dialogue Learning for Spoken Conversational Question Answering","created":"2021-06-04","cited_by_count":28},{"id":"2010.11066","title":"Contextualized Attention-based Knowledge Transfer for Spoken Conversational Question Answering","created":"2020-10-21","cited_by_count":27},{"id":"2204.11677","title":"Conversational Question Answering on Heterogeneous Sources","created":"2022-04-25","cited_by_count":26},{"id":"2108.02866","title":"Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering","created":"2021-08-05","cited_by_count":25},{"id":"2402.14361","title":"OpenTab: Advancing Large Language Models as Open-domain Table Reasoners","created":"2024-02-22","cited_by_count":25},{"id":"2402.12869","title":"Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data","created":"2024-02-20","cited_by_count":24},{"id":"2305.19912","title":"Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data","created":"2023-05-31","cited_by_count":23},{"id":"2201.10866","title":"CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search","created":"2022-01-26","cited_by_count":21},{"id":"2303.10368","title":"An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering","created":"2023-03-18","cited_by_count":19},{"id":"2306.07597","title":"Question Decomposition Tree for Answering Complex Questions over Knowledge Bases","created":"2023-06-13","cited_by_count":15},{"id":"2210.12338","title":"Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge","created":"2022-10-22","cited_by_count":14},{"id":"2305.02564","title":"RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","created":"2023-05-04","cited_by_count":13},{"id":"2402.15400","title":"Faithful Temporal Question Answering over Heterogeneous Sources","created":"2024-02-23","cited_by_count":13},{"id":"2306.12235","title":"CompMix: A Benchmark for Heterogeneous Question Answering","created":"2023-06-21","cited_by_count":12},{"id":"2108.04049","title":"Multi-modal Retrieval of Tables and Texts Using Tri-encoder Models","created":"2021-08-09","cited_by_count":11},{"id":"2108.08597","title":"Beyond NED: Fast and Effective Search Space Reduction for Complex Question Answering over Knowledge Bases","created":"2021-08-19","cited_by_count":11},{"id":"2402.11855","title":"TriSampler: A Better Negative Sampling Principle for Dense Retrieval","created":"2024-02-19","cited_by_count":10},{"id":"2407.03604","title":"Modality-Specialized Synergizers for Interleaved Vision-Language Generalists","created":"2024-07-04","cited_by_count":9},{"id":"2201.05409","title":"Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval","created":"2022-01-14","cited_by_count":7}],"next_cursor":null}