Data to 7 Oct 2026

Relevance-guided Supervision for OpenQA with ColBERT

arXiv 2007.00814 ↗First posted 1 Jul 2020cs.CL cs.IRcited by 71

Not on the map. Why?

Abstract (arXiv)

Systems for Open-Domain Question Answering (OpenQA) generally depend on a retriever for finding candidate passages in a large corpus and a reader for extracting answers from those passages. In much recent work, the retriever is a learned component that uses coarse-grained vector representations of questions and passages. We argue that this modeling choice is insufficiently expressive for dealing with the complexity of natural language questions. To address this, we define ColBERT-QA, which adapts the scalable neural retrieval model ColBERT to OpenQA. ColBERT creates fine-grained interactions between questions and passages. We propose an efficient weak supervision strategy that iteratively uses ColBERT to create its own training data. This greatly improves OpenQA retrieval on Natural Questions, SQuAD, and TriviaQA, and the resulting system attains state-of-the-art extractive OpenQA performance on all three datasets.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 14; 2023: 15; 2024: 12; 2025: 11; 2026: 2.

71 papers.

Sort:

By area:

2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
2022X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrievalcited by 279
2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 259
2023Landmark Attention: Random-Access Infinite Context Length for Transformerscited by 206
2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
2023Evaluating Open-Domain Question Answering in the Era of Large Language Modelscited by 110

38 more

2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
2022PLAID: An Efficient Engine for Late Interaction Retrievalcited by 95
2021Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrievalcited by 63
2024TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Modelscited by 63
2021MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documentscited by 53
2022Questions Are All You Need to Train a Dense Passage Retrievercited by 47
2022Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformercited by 45
2021Multi-task Retrieval for Knowledge-Intensive Taskscited by 44
2021Hindsight: Posterior-guided training of retrievers for improved open-ended generationcited by 38
2021R2-D2: A Modular Baseline for Open-Domain Question Answeringcited by 37
2024The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Surveycited by 32
2021Challenges in Generalization in Open Domain Question Answeringcited by 30
2023Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Usecited by 27
2023Large Language Models are Built-in Autoregressive Search Enginescited by 26
2022A Survey for Efficient Open Domain Question Answeringcited by 20
2021You Only Need One Model for Open-domain Question Answeringcited by 17
2021Learning Cross-Lingual IR from an English Retrievercited by 16
2021Attention-guided Generative Models for Extractive Question Answeringcited by 14
2021Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Frameworkcited by 11
2024SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsingcited by 11
2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generationcited by 10
2025ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidancecited by 10
2024Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answeringcited by 8
2025Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notescited by 7
2021Pruning the Index Contents for Memory Efficient Open-Domain QAcited by 6
2022Optimizing Test-Time Query Representations for Dense Retrievalcited by 6
2022Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Modelscited by 6
2022Variational Open-Domain Question Answeringcited by 5
2024A Survey of Generative Information Retrievalcited by 4
2021Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefitscited by 3
2022Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answeringcited by 3
2022Fast and Light-Weight Answer Text Retrieval in Dialogue Systemscited by 2
2023BRENT: Bidirectional Retrieval Enhanced Norwegian Transformercited by 2
2023GPT-3 Models are Few-Shot Financial Reasonerscited by 2
2025Multimodal semantic retrieval for product searchcited by 2
2025From Retrieval to Generation: Comparing Different Approachescited by 2
2025ExpertRAG: Efficient RAG with Mixture of Experts -- Optimizing Context Retrieval for Adaptive LLM Responsescited by 2
2025An evaluation of LLMs for generating movie reviews: GPT-4o, Gemini-2.0 and DeepSeek-V3cited by 2

50 most cited of 71 All 71 (JSON)