mlsanityData to 7 Oct 2026

One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval

arXiv 2107.11976 ↗First posted 26 Jul 2021cs.CLcited by 46

Not on the map. Why?

Abstract (arXiv)

We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first unified many-to-many question answering (QA) model that can answer questions across many languages, even for ones without language-specific annotated data or knowledge sources. We introduce a new dense passage retrieval algorithm that is trained to retrieve documents across languages for a question. Combined with a multilingual autoregressive generation model, CORA answers directly in the target language without any translation or in-language retrieval modules as used in prior work. We propose an iterative training method that automatically extends annotated data available only in high-resource languages to low-resource ones. Our results show that CORA substantially outperforms the previous state of the art on multilingual open QA benchmarks across 26 languages, 9 of which are unseen during training. Our analyses show the significance of cross-lingual retrieval and generation in many languages, particularly under low-resource settings.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Builds on 37 of its 61 references that are in the map. First posted on arXiv 26 Jul 2021.

Builds on

37 of 61 references.

References · 37

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  7. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  9. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  10. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  11. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  12. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
25 more
  1. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  2. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 486
  3. 2020Pretrained Transformers for Text Ranking: BERT and Beyondcited by 266
  4. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  5. 2018Marian: Fast Neural Machine Translation in C++cited by 202
  6. 2020MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answeringcited by 151
  7. 2019Synthetic QA Corpora Generation with Roundtrip Consistencycited by 143
  8. 2019Learning Dense Representations for Entity Retrievalcited by 122
  9. 2020XOR QA: Cross-lingual Open-Retrieval Question Answeringcited by 121
  10. 201975 Languages, 1 Model: Parsing Universal Dependencies Universallycited by 90
  11. 2019A Discrete Hard EM Approach for Weakly Supervised Question Answeringcited by 78
  12. 2021Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representationscited by 60
  13. 2018What Makes Reading Comprehension Questions Easier?cited by 59
  14. 2020Cross-lingual Retrieval for Iterative Self-Supervised Trainingcited by 54
  15. 2020Entity Linking in 100 Languagescited by 52
  16. 2021NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learnedcited by 52
  17. 2021Multilingual Autoregressive Entity Linkingcited by 50
  18. 2020Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpuscited by 49
  19. 2020Challenges in Information-Seeking QA: Unanswerable Questions and Paragraph Retrievalcited by 44
  20. 2020Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answeringcited by 41
  21. 2020Towards Zero-Shot Multilingual Synthetic Question and Answer Generation for Cross-Lingual Reading Comprehensioncited by 17
  22. 2019Polyglot Contextual Representations Improve Crosslingual Transfercited by 16
  23. 2019Semantic Role Labeling with Iterative Structure Refinementcited by 5
  24. 2019Low-Resource Parsing with Crosslingual Contextualized Representationscited by 5
  25. 2016Learning to Translate for Multilingual Question Answeringcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 10; 2023: 12; 2024: 13; 2025: 4; 2026: 4.

46 papers.

Sort:

By area:

  1. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  2. 2023Augmented Language Models: a Surveycited by 398
  3. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  4. 2022Task-aware Retrieval with Instructionscited by 107
  5. 2024Best Practices and Lessons Learned on Synthetic Datacited by 104
  6. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73
  7. 2023GEO: Generative Engine Optimizationcited by 53
  8. 2023Explaining Legal Concepts with Augmented Large Language Models (GPT-4)cited by 39
  9. 2024BERGEN: A Benchmarking Library for Retrieval-Augmented Generationcited by 31
  10. 2024Retrieval-augmented generation in multilingual settingscited by 27
  11. 2022Towards Best Practices for Training Multilingual Dense Retrieval Modelscited by 26
  12. 2022English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddingscited by 26
34 more
  1. 2024Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generationcited by 25
  2. 2023Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrievalcited by 24
  3. 2023Evaluating and Modeling Attribution for Cross-Lingual Question Answeringcited by 21
  4. 2023From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICLcited by 17
  5. 2023AutoKG: Efficient Automated Knowledge Graph Generation for Language Modelscited by 17
  6. 2021Learning Cross-Lingual IR from an English Retrievercited by 16
  7. 2023keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLMcited by 16
  8. 2022DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Enginecited by 15
  9. 2022CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrievalcited by 14
  10. 2024Teaching LLMs to Abstain across Languages via Multilingual Feedbackcited by 14
  11. 2024Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustnesscited by 13
  12. 2022MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languagescited by 11
  13. 2025On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generationcited by 10
  14. 2023Survey on Memory-Augmented Neural Networks: Cognitive Insights to AI Applicationscited by 7
  15. 2021Cross-Lingual Open-Domain Question Answering with Answer Sentence Generationcited by 6
  16. 2023Learning to Generalize for Cross-domain QAcited by 6
  17. 2024HyQE: Ranking Contexts with Hypothetical Query Embeddingscited by 6
  18. 2024Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generationcited by 6
  19. 2022Twist Decoding: Diverse Generators Guide Each Othercited by 4
  20. 2023Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attentioncited by 4
  21. 2025The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corporacited by 4
  22. 2023Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrievalcited by 3
  23. 2024Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervisioncited by 3
  24. 2024Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labelingcited by 3
  25. 2025CLIRudit: Cross-Lingual Information Retrieval of Scientific Documentscited by 2
  26. 2026All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAGcited by 2
  27. 2022ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering Systemcited by 1
  28. 2022Cross-Lingual QA as a Stepping Stone for Monolingual Open QA in Icelandiccited by 1
  29. 2022MIA 2022 Shared Task Submission: Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answeringcited by 1
  30. 2026Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Contentcited by 1
  31. 2024Domain Adaptation of Multilingual Semantic Search -- Literature Reviewcited by 0
  32. 2025Few-Shot Multilingual Open-Domain QA from 5 Examplescited by 0
  33. 2026Multilingual Reasoning Cascades Need More Contextcited by 0
  34. 2026Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAGcited by 0