ACL Findings2023
RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering
Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Yang Wang, Zhiheng Huang, Bing Xiang, Dan Roth
Abstract
Open-domain question answering (ODQA) is a crucial task in natural language processing. A typical ODQA system relies on a retriever module to select relevant contexts from a large corpus for a downstream reading comprehension model. Existing ODQA datasets consist mainly of Wikipedia corpus, and are insufficient to study models' generalizability across diverse domains, as models are trained and evaluated on the same genre of data. We propose RobustQA 1 , a novel benchmark consisting of datasets from 8 different domains, which facilitates the evaluation of ODQA's domain robustness. To build RobustQA, we annotate QA pairs in retrieval datasets with rigorous quality control. We further examine improving QA performances by incorporating unsupervised learning methods with target-domain corpus and adopting large generative language models. These methods can effectively improve model performances on RobustQA. However, experimental results demonstrate a significant gap from in-domain training, suggesting that Ro-bustQA is a challenging benchmark to evaluate ODQA domain robustness.
1 Datasets and their processing code can be found here: https://github.com/rujunhan/RobustQA-data FiQA-Finance Question: Why do investors buy stock that had appreciated? Document: Imagine how foolish the people that bought Apple at 10 it traded at just years prior, how could it go any higher? Stocks have no memory. A stock's earnings may grow and justify the new higher price people are willing to pay. When FB came public, I remarked how I'd analyze the price and felt it was overvalued until its earnings came up. Just because it's gone down ever since, doesn't make it a buy, yet.
Question: What techniques, tricks or otherwise have you used to get upgrades on flights? Document: ... but I think the best way to get upgraded is to fly a lot with the airline. Generally when the flight's overbooked in one class, and they're trying to pick which person to upgrade, frequent flyer status is the first metric they use. The higher your status, the higher up the list you go! Having a high status with a partner airline can work too, high tiers with a partner airline usually comes below the airline's own frequent flyers, but above everyone else. Otherwise, if you're flying on your own that'll help in the event that there aren't enough frequent flyer to upgrade to free the required number of seats! Offering to pay may be an option too -if they're pretty full they may offer you a low price to upgrade.
Ask Lune
Ask anything. The answer quotes the paper.
Lune reads all of it and the papers around it, then shows you the passages behind every answer.
Lune answers from
the full paper · 6 top-tier papers that cite it · related work
Free to start. No credit card required.
Cited by top-tier papers6
- RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question AnsweringRujun Han, Yuhao Zhang, Peng Qi, Yumo Xu et al.EMNLP 2024 · 10 citations
- Designing Staged Evaluation Workflows for LLMs: Integrating Domain Experts, Lay Users, and Model-Generated Evaluation CriteriaAnnalisa Szymanski, Simret Araya Gebreegziabher, Oghenemaro Anuyah, Ronald A. Metoyer et al.CHI 2026 · 1 citation
- Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR BenchmarksMinjeong Ban, Jeonghwan Choi, Hyangsuk Min, Nicole Hee-Yeon Kim et al.ICLR 2026 · 1 citation
- RAG-Zeval: Enhancing RAG Responses Evaluator through End-to-End Reasoning and Ranking-Based Reinforcement LearningKun Li, Yunxiang Li, Tianhua Zhang, Hongyin Luo et al.EMNLP 2025 · 1 citation
- Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language ModelsZhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu et al.EMNLP 2024
Builds on5
- In Search of Lost Domain GeneralizationIshaan Gulrajani, David Lopez-PazICLR 2021 · 1,416 citations
- Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware SamplingSebastian Hofstätter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin et al.SIGIR 2021 · 297 citations
- TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence SelectionSiddhant Garg, Thuy Vu, Alessandro MoschittiAAAI 2020 · 229 citations
- Task-aware Retrieval with InstructionsAkari Asai, Timo Schick, Patrick Lewis, Xilun Chen et al.ACL Findings 2023 · 45 citations
- ECONET: Effective Continual Pretraining of Language Models for Event Temporal ReasoningRujun Han, Xiang Ren, Nanyun PengEMNLP 2021 · 31 citations
Related papers
- Robust Domain Adaptation for Machine Reading ComprehensionLiang Jiang, Zhenyu Huang, Jia Liu, Zujie Wen et al.AAAI 2023 · 1 citation
- Exploiting Abstract Meaning Representation for Open-Domain Question AnsweringCunxiang Wang, Zhikun Xu, Qipeng Guo, Xiangkun Hu et al.ACL Findings 2023 · 5 citations
- Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question AnsweringMingxuan Ju, Wenhao Yu, Tong Zhao, Chuxu Zhang et al.EMNLP Findings 2022 · 21 citations
- Open-domain Question Answering via Chain of Reasoning over Heterogeneous KnowledgeKaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg et al.EMNLP Findings 2022 · 16 citations
- One Question Answering Model for Many Languages with Cross-lingual Dense Passage RetrievalAkari Asai, Xinyan Yu, Jungo Kasai, Hanna HajishirziNeurIPS 2021 · 86 citations
