mlsanityData to 7 Oct 2026

Learning to Generalize for Cross-domain QA

arXiv 2305.08208 ↗First posted 14 May 2023cs.CL cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

There have been growing concerns regarding the out-of-domain generalization ability of natural language processing (NLP) models, particularly in question-answering (QA) tasks. Current synthesized data augmentation methods for QA are hampered by increased training costs. To address this issue, we propose a novel approach that combines prompting methods and linear probing then fine-tuning strategy, which does not entail additional cost. Our method has been theoretically and empirically shown to be effective in enhancing the generalization ability of both generative and discriminative models. Our approach outperforms state-of-the-art baselines, with an average increase in F1 score of 4.5%-7.9%. Furthermore, our method can be easily integrated into any pre-trained models and offers a promising solution to the under-explored cross-domain QA task. We release our source code at GitHub*.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 35 of its 43 references that are in the map. First posted on arXiv 14 May 2023.

Builds on

35 of 43 references.

References · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  8. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  9. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
  10. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  11. 2017The NarrativeQA Reading Comprehension Challengecited by 590
  12. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 428
23 more
  1. 2019Linguistic Knowledge and Transferability of Contextual Representationscited by 382
  2. 2016NewsQA: A Machine Comprehension Datasetcited by 330
  3. 2020On the Theory of Transfer Learning: The Importance of Task Diversitycited by 186
  4. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 169
  5. 2020Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasetscited by 137
  6. 2020Understanding and Improving Information Transfer in Multi-Task Learningcited by 113
  7. 2021Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Taskscited by 100
  8. 2021Contrastive Explanations for Model Interpretabilitycited by 75
  9. 2021Template-free Prompt Tuning for Few-shot NERcited by 73
  10. 2020Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactualscited by 67
  11. 2022Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settingscited by 66
  12. 2020Explaining The Efficacy of Counterfactually Augmented Datacited by 64
  13. 2021Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?cited by 62
  14. 2022PromDA: Prompt-based Data Augmentation for Low-Resource NLU Taskscited by 51
  15. 2021One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrievalcited by 46
  16. 2020What do Models Learn from Question Answering Datasets?cited by 45
  17. 2017Making Neural QA as Simple as Possible but not Simplercited by 33
  18. 2021Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysiscited by 30
  19. 2021Challenges in Generalization in Open Domain Question Answeringcited by 30
  20. 2022A Rationale-Centric Framework for Human-in-the-loop Machine Learningcited by 27
  21. 2019Unsupervised Domain Adaptation on Reading Comprehensioncited by 14
  22. 2022Towards Fine-grained Causal Reasoning and QAcited by 13
  23. 2022Synthetic Question Value Estimation for Domain Adaptation of Question Answeringcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 0; 2026: 2.

6 papers.

  1. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 261
  2. 2024Contrastive Instruction Tuningcited by 17
  3. 2024Evaluating Financial Relational Graphs: Interpretation Before Predictioncited by 5
  4. 2023Out-of-Distribution Generalization in Text Classification: Past, Present, and Futurecited by 1
  5. 2026Relational Probing: LM-to-Graph Adaptation for Financial Predictioncited by 0
  6. 2026Can LoRA Fusion Support Cross-Domain Tasks in Cloud-Edge Collaboration?cited by 0