Data to 7 Oct 2026

UnitedQA: A Hybrid Approach for Open Domain Question Answering

arXiv 2101.00178 ↗First posted 1 Jan 2021cs.CL cs.AIcited by 42

Not on the map. Why?

Abstract (arXiv)

To date, most of recent work under the retrieval-reader framework for open-domain QA focuses on either extractive or generative reader exclusively. In this paper, we study a hybrid approach for leveraging the strengths of both models. We apply novel techniques to enhance both extractive and generative readers built upon recent pretrained neural language models, and find that proper training methods can provide large improvement over previous state-of-the-art models. We demonstrate that a simple hybrid approach by combining answers from both readers can efficiently take advantages of extractive and generative answer inference strategies and outperforms single models as well as homogeneous ensembles. Our approach outperforms previous state-of-the-art models by 3.3 and 2.7 points in exact match on NaturalQuestions and TriviaQA respectively.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 27 of its 35 references that are in the map. First posted on arXiv 1 Jan 2021.

Builds on

27 of 35 references.

References · 27

2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
2015Distilling the Knowledge in a Neural Networkcited by 10,076
2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918

15 more

2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 413
2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
2019SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimizationcited by 253
2018Neural Approaches to Conversational AIcited by 164
2020Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasetscited by 137
2017Simple and Effective Multi-Paragraph Reading Comprehensioncited by 120
2016Robust Large Margin Deep Neural Networkscited by 117
2019Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answeringcited by 96
2020Pre-training via Paraphrasingcited by 92
2019A Discrete Hard EM Approach for Weakly Supervised Question Answeringcited by 78
2020Posterior Differential Regularization with f-divergence for Improving Model Robustnesscited by 20
2019Technical report on Conversational Question Answeringcited by 18
2020Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answeringcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 10; 2023: 8; 2024: 12; 2025: 4; 2026: 1.

42 papers.

Sort:

By area:

2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
2022Teaching language models to support answers with verified quotescited by 290
2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 104
2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 66
2025Retrieval-Augmented Generation with Conflicting Evidencecited by 60
2024When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentationcited by 59
2022Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformercited by 45
2022Neural Approaches to Conversational Information Retrievalcited by 41

30 more

2021R2-D2: A Modular Baseline for Open-Domain Question Answeringcited by 37
2021Open Domain Question Answering with A Unified Knowledge Interfacecited by 32
2023Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Trainingcited by 31
2022A Survey of Knowledge-Intensive NLP with Pre-Trained Language Modelscited by 30
2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
2023HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responsescited by 25
2024Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Modelscited by 23
2022A Survey for Efficient Open Domain Question Answeringcited by 20
2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
2021You Only Need One Model for Open-domain Question Answeringcited by 17
2022Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledgecited by 14
2021Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Frameworkcited by 11
2022Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answeringcited by 11
2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generationcited by 10
2024Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answeringcited by 8
2023Long-Tailed Question Answering in an Open Worldcited by 7
2024Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Modelscited by 7
2021Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literaturecited by 6
2022Optimizing Test-Time Query Representations for Dense Retrievalcited by 6
2023Plug-and-Play Knowledge Injection for Pre-trained Language Modelscited by 6
2022FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answeringcited by 5
2023When to Read Documents or QA History: On Unified and Selective Open-domain QAcited by 3
2025EmoRAG: Evaluating RAG Robustness to Symbolic Perturbationscited by 3
2024FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selectioncited by 2
2023On Monotonic Aggregation for Open-domain QAcited by 1
2024GOVERN: Gradient Orientation Vote Ensemble for Multi-Teacher Reinforced Distillationcited by 1
2024MaxMind: A Memory Loop Network to Enhance Software Productivity based on Large Language Modelscited by 1
2024KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learningcited by 0
2025AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settingscited by 0
2026Guaranteeing Faithful Evidence Extraction in Speculative Retrieval-Augmented Generationcited by 0