{"total":96,"rows":[{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952,"area":"rag"},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244,"area":null},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226,"area":null},{"id":"2101.00774","title":"Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering","created":"2021-01-04","cited_by_count":178,"area":null},{"id":"2110.07367","title":"RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking","created":"2021-10-14","cited_by_count":176,"area":null},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151,"area":null},{"id":"2306.05817","title":"How Can Recommender Systems Benefit from Large Language Models: A Survey","created":"2023-06-09","cited_by_count":142,"area":null},{"id":"2106.05346","title":"End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering","created":"2021-06-09","cited_by_count":133,"area":"rag"},{"id":"2401.06104","title":"Transformers are Multi-State RNNs","created":"2024-01-11","cited_by_count":120,"area":"inference"},{"id":"2110.00768","title":"TopiOCQA: Open-domain Conversational Question Answering with Topic Switching","created":"2021-10-02","cited_by_count":96,"area":null},{"id":"2311.08377","title":"Learning to Filter Context for Retrieval-Augmented Generation","created":"2023-11-14","cited_by_count":83,"area":"rag"},{"id":"2208.00748","title":"Efficient Long-Text Understanding with Short-Text Models","created":"2022-08-01","cited_by_count":71,"area":null},{"id":"2110.04330","title":"KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering","created":"2021-10-08","cited_by_count":67,"area":null},{"id":"2102.13558","title":"Natural Language Video Localization: A Revisit in Span-based Question Answering Framework","created":"2021-02-26","cited_by_count":55,"area":null},{"id":"2401.11911","title":"Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?","created":"2024-01-22","cited_by_count":48,"area":null},{"id":"2302.14502","title":"A Survey on Long Text Modeling with Transformers","created":"2023-02-28","cited_by_count":47,"area":null},{"id":"2101.00117","title":"Multi-task Retrieval for Knowledge-Intensive Tasks","created":"2021-01-01","cited_by_count":44,"area":null},{"id":"2101.00178","title":"UnitedQA: A Hybrid Approach for Open Domain Question Answering","created":"2021-01-01","cited_by_count":42,"area":null},{"id":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40,"area":null},{"id":"2411.02886","title":"TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection","created":"2024-11-05","cited_by_count":39,"area":"inference"},{"id":"2503.15888","title":"Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models","created":"2025-03-20","cited_by_count":39,"area":"rag"},{"id":"2109.03502","title":"R2-D2: A Modular Baseline for Open-Domain Question Answering","created":"2021-09-08","cited_by_count":37,"area":null},{"id":"2210.16773","title":"An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks","created":"2022-10-30","cited_by_count":36,"area":"rag"},{"id":"2401.15269","title":"Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models","created":"2024-01-27","cited_by_count":34,"area":"lr"},{"id":"2402.09760","title":"Grounding Language Model with Chunking-Free In-Context Retrieval","created":"2024-02-15","cited_by_count":30,"area":"rag"},{"id":"2109.06747","title":"Adaptive Information Seeking for Open-Domain Question Answering","created":"2021-09-14","cited_by_count":29,"area":null},{"id":"2410.02703","title":"Selective Attention Improves Transformer","created":"2024-10-03","cited_by_count":26,"area":null},{"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,"area":null},{"id":"2405.12701","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","created":"2024-05-21","cited_by_count":20,"area":null},{"id":"2412.01456","title":"Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and Beyond","created":"2024-12-02","cited_by_count":15,"area":null},{"id":"2502.21024","title":"TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions","created":"2025-02-28","cited_by_count":15,"area":null},{"id":"2110.06393","title":"Attention-guided Generative Models for Extractive Question Answering","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2201.05299","title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering","created":"2022-01-14","cited_by_count":13,"area":null},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","cited_by_count":13,"area":null},{"id":"2401.05736","title":"Cross-modal Retrieval for Knowledge-based Visual Question Answering","created":"2024-01-11","cited_by_count":13,"area":null},{"id":"2504.00573","title":"Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models","created":"2025-04-01","cited_by_count":13,"area":"rag"},{"id":"2105.12932","title":"Contrastive Fine-tuning Improves Robustness for Neural Rankers","created":"2021-05-27","cited_by_count":12,"area":null},{"id":"2205.11729","title":"From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2102.08633","title":"Open-Retrieval Conversational Machine Reading","created":"2021-02-17","cited_by_count":11,"area":null},{"id":"2205.00820","title":"Entity-aware Transformers for Entity Search","created":"2022-05-02","cited_by_count":10,"area":null},{"id":"2309.14735","title":"Legal Question-Answering in the Indian Context: Efficacy, Challenges, and Potential of Modern AI Models","created":"2023-09-26","cited_by_count":10,"area":null},{"id":"2109.12264","title":"More Than Reading Comprehension: A Survey on Datasets and Metrics of Textual Question Answering","created":"2021-09-25","cited_by_count":8,"area":null},{"id":"2110.01599","title":"Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering","created":"2021-10-04","cited_by_count":8,"area":null},{"id":"2210.00185","title":"Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks","created":"2022-10-01","cited_by_count":8,"area":null},{"id":"2210.11708","title":"Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning","created":"2022-10-21","cited_by_count":8,"area":"lr"},{"id":"2106.04134","title":"Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2209.01621","title":"Interactive Question Answering Systems: Literature Review","created":"2022-09-04","cited_by_count":7,"area":null},{"id":"2510.13843","title":"Serialized EHR make for good text representations","created":"2025-10-11","cited_by_count":7,"area":null},{"id":"2102.10697","title":"Pruning the Index Contents for Memory Efficient Open-Domain QA","created":"2021-02-21","cited_by_count":6,"area":null},{"id":"2110.11869","title":"FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks","created":"2021-09-12","cited_by_count":5,"area":null},{"id":"2211.10147","title":"FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering","created":"2022-11-18","cited_by_count":5,"area":null},{"id":"2407.03627","title":"DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation","created":"2024-07-04","cited_by_count":5,"area":"rag"},{"id":"2507.06782","title":"Temporal Information Retrieval via Time-Specifier Model Merging","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2103.03820","title":"AnswerQuest: A System for Generating Question-Answer Items from Multi-Paragraph Documents","created":"2021-03-05","cited_by_count":4,"area":null},{"id":"2107.02102","title":"Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints","created":"2021-07-05","cited_by_count":4,"area":null},{"id":"2111.11992","title":"Sparse Fusion for Multimodal Transformers","created":"2021-11-23","cited_by_count":4,"area":null},{"id":"2308.06431","title":"Performance Prediction for Multi-hop Questions","created":"2023-08-12","cited_by_count":4,"area":null},{"id":"2309.13218","title":"Language Models for Business Optimisation with a Real World Case Study in Production Scheduling","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2405.07615","title":"ViWikiFC: Fact-Checking for Vietnamese Wikipedia-Based Textual Knowledge Source","created":"2024-05-13","cited_by_count":4,"area":null},{"id":"2206.15428","title":"Test2Vec: An Execution Trace Embedding for Test Case Prioritization","created":"2022-06-28","cited_by_count":3,"area":null},{"id":"2210.01989","title":"WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2303.12029","title":"Wearing Masks Implies Refuting Trump?: Towards Target-specific User Stance Prediction across Events in COVID-19 and US Election 2020","created":"2023-03-21","cited_by_count":3,"area":null},{"id":"2308.09308","title":"Differentiable Retrieval Augmentation via Generative Language Modeling for E-commerce Query Intent Classification","created":"2023-08-18","cited_by_count":3,"area":null},{"id":"2404.02933","title":"NL2KQL: From Natural Language to Kusto Query","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2406.19391","title":"Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across Heads","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2602.04711","title":"Addressing Corpus Knowledge Poisoning Attacks on RAG Using Sparse Attention","created":"2026-02-04","cited_by_count":3,"area":"rag"},{"id":"2211.16029","title":"Diverse Multi-Answer Retrieval with Determinantal Point Processes","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2302.01806","title":"Mitigating Data Scarcity for Large Language Models","created":"2023-02-03","cited_by_count":2,"area":null},{"id":"2309.04979","title":"Retrieval-Augmented Meta Learning for Low-Resource Text Classification","created":"2023-09-10","cited_by_count":2,"area":"rag"},{"id":"2311.01372","title":"Data-Augmented and Retrieval-Augmented Context Enrichment in Chinese Media Bias Detection","created":"2023-11-02","cited_by_count":2,"area":"rag"},{"id":"2411.03542","title":"Exploring the Benefits of Domain-Pretraining of Generative Large Language Models for Chemistry","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2203.16187","title":"Auto-MLM: Improved Contrastive Learning for Self-supervised Multi-lingual Knowledge Retrieval","created":"2022-03-30","cited_by_count":1,"area":null},{"id":"2205.00042","title":"Answer Consolidation: Formulation and Benchmarking","created":"2022-04-29","cited_by_count":1,"area":null},{"id":"2305.15516","title":"Free Lunch for Efficient Textual Commonsense Integration in Language Models","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2306.04758","title":"SKG: A Versatile Information Retrieval and Analysis Framework for Academic Papers with Semantic Knowledge Graphs","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2312.08299","title":"Conceptualizing Suicidal Behavior: Utilizing Explanations of Predicted Outcomes to Analyze Longitudinal Social Media Data","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2406.13232","title":"Towards Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2412.14751","title":"Query pipeline optimization for cancer patient question answering systems","created":"2024-12-19","cited_by_count":1,"area":"rag"},{"id":"2503.06137","title":"Evaluating Discourse Cohesion in Pre-trained Language Models","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2510.20926","title":"FicSim: A Dataset for Multi-Faceted Semantic Similarity in Long-Form Fiction","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2101.01910","title":"SF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering","created":"2021-01-06","cited_by_count":0,"area":null},{"id":"2103.00728","title":"BERT-based knowledge extraction method of unstructured domain text","created":"2021-03-01","cited_by_count":0,"area":null},{"id":"2109.08650","title":"Towards Handling Unconstrained User Preferences in Dialogue","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2111.10044","title":"Building a Question Answering System for the Manufacturing Domain","created":"2021-11-19","cited_by_count":0,"area":null},{"id":"2202.09955","title":"StyleBERT: Chinese pretraining by font style information","created":"2022-02-21","cited_by_count":0,"area":null},{"id":"2206.08046","title":"An Open-Domain QA System for e-Governance","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2304.01638","title":"Multidimensional Perceptron for Efficient and Explainable Long Text Classification","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2304.06623","title":"Exploring the State of the Art in Legal QA Systems","created":"2023-04-13","cited_by_count":0,"area":null},{"id":"2305.03519","title":"Leveraging BERT Language Model for Arabic Long Document Classification","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2307.02300","title":"Improving Address Matching using Siamese Transformer Networks","created":"2023-07-05","cited_by_count":0,"area":null},{"id":"2311.01571","title":"On Preserving the Knowledge of Long Clinical Texts","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2502.12124","title":"RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents","created":"2025-02-17","cited_by_count":0,"area":"rag"},{"id":"2506.19258","title":"Personality Prediction from Life Stories using Language Models","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2607.18825","title":"AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.31568","title":"DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education","created":"2026-09-25","cited_by_count":0,"area":"agents"}],"next_cursor":null}