Papers › UnitedQA: A Hybrid Approach for Open Domain Question Answering
UnitedQA: A Hybrid Approach for Open Domain Question Answering
Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao
To date, most of recent work under the retrieval-reader framework for open-domain QA focuses on either extractive or generative reader exclusively. In this paper, we study a hybrid approach for leveraging the strengths of both models. We apply novel techniques to enhance both extractive and generative readers built upon recent pretrained neural language models, and find that proper training methods can provide large improvement over previous state-of-the-art models. We demonstrate that a simple hybrid approach by combining answers from both readers can efficiently take advantages of extractive and generative answer inference strategies and outperforms single models as well as homogeneous ensembles. Our approach outperforms previous state-of-the-art models by 3.3 and 2.7 points in exact match on NaturalQuestions and TriviaQA respectively.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Open-Domain Question Answering | Natural Questions | UnitedQA (Hybrid) | Exact Match | 54.7 | #4 of 5 | Archive leaderboard | report |
| Open-Domain Question Answering | TriviaQA | UnitedQA (Hybrid) | Exact Match | 70.5 | #1 of 1 | Archive leaderboard | report |
| Question Answering | EfficientQA dev | UnitedQA | Accuracy | 54.1 | #1 of 1 | Archive leaderboard | report |
| Question Answering | EfficientQA test | UnitedQA | Accuracy | 54 | #1 of 1 | Archive leaderboard | report |
| Question Answering | Natural Questions (long) | UnitedQA (Hybrid) | EM | 54.7 | #12 of 13 | Archive leaderboard | report |
| Question Answering | TriviaQA | UnitedQA (Hybrid reader) | F1 | 70.3 | #54 of 56 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections