ACL Findings2023
Learning to Generalize for Cross-domain QA
Abstract
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 underexplored cross-domain QA task. We release our source code at Github * .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution cites On the Theory of Transfer Learning: The Importance of Task Diversity
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution cites Understanding and Improving Information Transfer in Multi-Task Learning
Builds on16
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-DistributionAnanya Kumar, Aditi Raghunathan, Robbie Matthew Jones, Tengyu Ma et al.ICLR 2022 · 911 citations
- Learning The Difference That Makes A Difference With Counterfactually-Augmented DataDivyansh Kaushik, Eduard H. Hovy, Zachary Chase LiptonICLR 2020 · 625 citations
- Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge BasesYu Gu, Sue Kase, Michelle Vanni, Brian M. Sadler et al.WWW 2021 · 304 citations
- On the Theory of Transfer Learning: The Importance of Task DiversityNilesh Tripuraneni, Michael I. Jordan, Chi JinNeurIPS 2020 · 263 citations
- Understanding and Improving Information Transfer in Multi-Task LearningSen Wu, Hongyang R. Zhang, Christopher RéICLR 2020 · 183 citations
Related papers
- MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question AnsweringXiusi Chen, Jyun-Yu Jiang, Wei-Cheng Chang, Cho-Jui Hsieh et al.ACL 2024 · 7 citations
- Breaking the Barrier Between Pre-training and Fine-tuning: A Hybrid Prompting Model for Knowledge-Based VQAZhongfan Sun, Yongli Hu, Qingqing Gao, Huajie Jiang et al.ACM MM 2023 · 6 citations
- PromDA: Prompt-based Data Augmentation for Low-Resource NLU TasksYufei Wang, Can Xu, Qingfeng Sun, Huang Hu et al.ACL 2022
- FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question AnsweringAkhil Kedia, Mohd Abbas Zaidi, Haejun LeeEMNLP 2022 · 11 citations
- Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data GenerationGuangzeng Han, Weisi Liu, Xiaolei HuangEMNLP Findings 2025 · 2 citations
