QAScore—An Unsupervised Unreferenced Metric for the Question Generation Evaluation
Open accessAbstract
Question Generation (QG) aims to automate the task of composing questions for a passage with a set of chosen answers found within the passage. In recent years, the introduction of neural generation models has resulted in substantial improvements of automatically generated questions in terms of quality, especially compared to traditional approaches that employ manually crafted heuristics. However, current QG evaluation metrics solely rely on the comparison between the generated questions and references, ignoring the passages or answers. Meanwhile, these metrics are generally criticized because of their low agreement with human judgement. We therefore propose a new reference-free evaluation metric called QAScore, which is capable of providing a better mechanism for evaluating QG systems. QAScore evaluates a question by computing the cross entropy according to the probability that the language model can correctly generate the masked words in the answer to that question. Compared to existing metrics such as BLEU and BERTScore, QAScore can obtain a stronger correlation with human judgement according to our human evaluation experiment, meaning that applying QAScore in the QG task benefits to a higher level of evaluation accuracy.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Visual question generation has been deployed in visual dialogue generation in a few works.
“Visual question generation has been deployed in visual dialogue generation in a few works [131, 133, 134].”
From Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications (2023) · cites this paper as [131]
In [131], QAScore is proposed using the pre-trained language model RoBERTa; it is reference-free and correlates well with human judgments.
“In [131], an evaluation metric called QAScore is proposed which makes use of pre-trained language model RoBERTa (Robustly Optimized BERT Pre-training Approach).”
From Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications (2023) · cites this paper as [131]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · see citing works
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344 · see citing works
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · see citing works
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515 · see citing works
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · see citing works
(2004) · Cited by 9,718 · see citing works
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · see citing works
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · see citing works
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319 · see citing works
(2005) · Cited by 4,152 · see citing works
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101 · see citing works
BERTScore: Evaluating Text Generation with BERT
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09675 · Cited by 2,865 · see citing works
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W., Salakhutdinov, R., & Manning, C. D. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1259 · Cited by 1,804 · see citing works
Reading Wikipedia to answer open-domain questions
Chen, D., Fisch, A., Weston, J., & Bordes, A. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1171 · Cited by 1,546 · see citing works
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
Shin, T., Razeghi, Y., Logan IV, R. L., Wallace, E., & Singh, S. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.346 · Cited by 1,279 · see citing works
BLEURT: Learning Robust Metrics for Text Generation
Sellam, T., Das, D., & Parikh, A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.704 · Cited by 1,005 · see citing works
NewsQA: A Machine Comprehension Dataset
Trischler, A., Wang, T., Yuan, X., Harris, J., Sordoni, A., Bachman, P., & Suleman, K. (2017) · Proceedings of the 2nd Workshop on Representation Learning for NLP · doi:10.18653/v1/w17-2623 · Cited by 706 · cited 2× · see citing works
“Although the aforementioned prevailing automatic metrics mentioned above are widely employed for QG evaluation, criticism of n -gram overlap-based metrics’ ability to accurately and comprehensively evaluate the quality has also been highlighted (Yuan et al., 2017).”
Learning to Ask: Neural Question Generation for Reading Comprehension
Du, X., Shao, J., & Cardie, C. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1123 · Cited by 696 · cited 1× · see citing works
“QG is highly related to the task of machine reading comprehension (MRC), which is a sub-task of question answering (QA) (Du et al., 2017; Xie et al., 2020; Pan et al., 2020a; Puri et al., 2020; Lyu et al., 2021; Chen et al., 2019; Li et al., 2021).”
The NarrativeQA Reading Comprehension Challenge
Kočiský, T., Schwarz, J., Blunsom, P., Dyer, C., Hermann, K. M., Melis, G., & Grefenstette, E. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00023 · Cited by 596 · cited 1× · see citing works
“Besides, QA can also be categorized into generative QA (Koˇciský et al., 2018; Xu et al., 2022) and extractive QA (Trischler et al., 2017; Lyu et al., 2022; Lewis et al., 2021; Zhang et al., 2020b).”
A Structured Review of the Validity of BLEU
Reiter, E. (2018) · Computational Linguistics · doi:10.1162/coli_a_00322 · Cited by 386 · see citing works
Improving Neural Question Generation Using Answer Separation
Kim, Y., Lee, H., Shin, J., & Jung, K. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33016602 · Cited by 178 · see citing works
Machine Comprehension by Text-to-Text Neural Question Generation
Yuan, X., Wang, T., Gülçehre, Ç., Sordoni, A., Bachman, P., Zhang, S., Subramanian, S., & Trischler, A. (2017) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w17-2603 · Cited by 158 · see citing works
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them
Lewis, P., Wu, Y., Liu, L., Minervini, P., Küttler, H., Piktus, A., Stenetorp, P., & Riedel, S. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00415 · Cited by 153 · see citing works
Can machine translation systems be evaluated by the crowd alone
Graham, Y., Baldwin, T., Moffat, A., & Zobel, J. (2015) · Natural Language Engineering · doi:10.1017/s1351324915000339 · Cited by 148 · see citing works
Self-citationRe-evaluating Automatic Summarization with BLEU and 192 Shades of ROUGE
Graham, Y. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1013 · Cited by 143 · see citing works
Self-citationTraining Question Answering Models From Synthetic Data
Puri, R., Spring, R., Shoeybi, M., Patwary, M. A., & Catanzaro, B. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.468 · Cited by 137 · see citing works
Reinforcement Learning Based Graph-to-Sequence Model for Natural Question GenerationPreprint
Chen, Y., Wu, L., & Zaki, M. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.04942 · Cited by 127 · see citing works
DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension
Saha, A., Aralikatte, R., Khapra, M. M., & Sankaranarayanan, K. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-1156 · Cited by 111 · see citing works
Towards a Better Metric for Evaluating Question Generation Systems
Nema, P., & Khapra, M. M. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1429 · Cited by 106 · see citing works
Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus
Liu, B., Wei, H., Niu, D., Chen, H., & He, Y. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3380270 · Cited by 89 · see citing works
Semantic Graphs for Generating Deep Questions
Pan, L., Xie, Y., Feng, Y., Chua, T., & Kan, M. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.135 · Cited by 85 · see citing works
Statistical Power and Translationese in Machine Translation Evaluation
Graham, Y., Haddow, B., & Koehn, P. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.6 · Cited by 83 · see citing works
Self-citationRecent Advances in Neural Question GenerationPreprint
Pan, L., Lei, W., Chua, T., & Kan, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.08949 · Cited by 79 · see citing works
Xu, Y., Wang, D., Yu, M., Ritchie, D., Yao, B., Wu, T., Zhang, Z., Li, T. J.-J., Bradford, N., Sun, B., et al. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.34 · Cited by 67 · see citing works
Achieving Reliable Human Assessment of Open-Domain Dialogue Systems
Ji, T., Graham, Y., Jones, G. J. F., Lyu, C., & Liu, Q. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.445 · Cited by 60 · see citing works
Self-citationImproving Question Generation with Sentence-Level Semantic Matching and Answer Position Inferring
Ma, X., Zhu, Q., Zhou, Y., & Li, X. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6366 · Cited by 56 · see citing works
EQG-RACE: Examination-Type Question Generation
Jia, X., Zhou, W., Sun, X., & Wu, Y. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i14.17553 · Cited by 48 · see citing works
Knowledge-Driven Distractor Generation for Cloze-Style Multiple Choice Questions
Ren, S., & Zhu, K. Q. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i5.16559 · Cited by 43 · see citing works
Answer-driven Deep Question Generation based on Reinforcement Learning
Wang, L., Xu, Z., Lin, Z., Zheng, H.-T., & Shen, Y. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.452 · Cited by 37 · see citing works
Improving Unsupervised Question Answering via Summarization-Informed Question Generation
Lyu, C., Shang, L., Graham, Y., Foster, J., Jiang, X., & Liu, Q. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.340 · Cited by 37 · see citing works
Self-citationAchieving Accurate Conclusions in Evaluation of Automatic Machine Translation Metrics
Graham, Y., & Liu, Q. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1001 · Cited by 27 · see citing works
Self-citationContrastive Multi-document Question Generation
Cho, W. S., Zhang, Y., Rao, S., Çelikyılmaz, A., Xiong, C., Gao, J., Wang, M., & Dolan, B. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-main.2 · Cited by 27 · see citing works
Exploring Question-Specific Rewards for Generating Deep Questions
Xie, Y., Pan, L., Wang, D., Kan, M., & Feng, Y. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.228 · Cited by 27 · see citing works
DATLMedQA: A Data Augmentation and Transfer Learning Based Solution for Medical Question Answering
Zhou, S., & Zhang, Y. (2021) · Applied Sciences · doi:10.3390/app112311251 · Cited by 16 · see citing works
QURIOUS: Question Generation Pretraining for Text GenerationPreprint
Narayan, S., Simões, G., Ma, J., Craighead, H., & McDonald, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.11026 · Cited by 12 · see citing works
Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism
Ji, T., Lyu, C., Cao, Z., & Cheng, P. (2021) · Entropy · doi:10.3390/e23111449 · Cited by 4 · see citing works
Self-citationContrasting Human Opinion of Non-factoid Question Answering with Automatic Evaluation
Ji, T., Graham, Y., & Jones, G. J. F. (2020) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3343413.3377996 · Cited by 3 · see citing works
Self-citationExtending the Scope of Out-of-Domain: Examining QA models in multiple subdomains
Lyu, C., Foster, J., & Graham, Y. (2022) · doi:10.18653/v1/2022.insights-1.4 · Cited by 3 · see citing works
Self-citationLi, J., Qu, K., Yan, J., Zhou, L., & Cheng, L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-82136-4_13 · Cited by 2 · see citing works
Self-citationLyu, C. (2023) · Dublin City University Open Access Institutional Repository (Dublin City University) · Cited by 1 · see citing works
Self-citationKnowledge-Driven Distractor Generation for Cloze-style Multiple Choice QuestionsPreprint
Ren, S., & Zhu, K. Q. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.09853
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805
Flagged first, then by citations
Research works printed but not linked: 2
- [22]Zhu F. Lei W. Wang C. Zheng J. Poria S. Chua T.S. Retrieving and reading: A comprehensive survey on open-domain question answering arXiv 2021 2101.00774
- [30]Zhang Z. Zhao H. Wang R. Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond arXiv 2020 cs.CL/2005.06249
Cited by
Sorted by citations
Mulla, N., & Gharpure, P. (2023) · Progress in Artificial Intelligence · doi:10.1007/s13748-023-00295-9 · Cited by 132 · see citing works
Large Language Models are Better Reasoners with Self-Verification
Weng, Y., Zhu, M., Xia, F., Li, B., He, S., Liu, S., Sun, B., Liu, K., & Zhao, J. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.167 · Cited by 110 · see citing works
Learnersourcing in the age of AI: Student, educator and machine partnerships for content creation
Khosravi, H., Denny, P. C., Moore, S., & Stamper, J. C. (2023) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2023.100151 · Cited by 65 · see citing works
Assessing the Quality of Multiple-Choice Questions Using GPT-4 and Rule-Based Methods
Moore, S., Nguyen, H. A., Chen, T., & Stamper, J. C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42682-7_16 · Cited by 43 · see citing works
Hwang, M.-H., Shin, J., Seo, H., Im, J.-S., Cho, H., & Lee, C.-K. (2023) · Applied Sciences · doi:10.3390/app13020903 · Cited by 25 · see citing works
QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation
Fu, W., Wei, B., Hu, J., Cai, Z., & Liu, J. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.658 · Cited by 16 · see citing works
“However, the criteria of human evaluations are varied in existing research, leading to inconsistent and unreliable evaluations of QG models (Ji et al., 2022) and automatic metrics (Amidei et al., 2018; Mulla and Gharpure, 2023).”
BackgroundOpinerium: Subjective Question Generation Using Large Language Models
Babakhani, P., Lommatzsch, A., Brodt, T., Sacker, D., Sivrikaya, F., & Albayrak, Ş. (2024) · IEEE Access · doi:10.1109/access.2024.3398553 · Cited by 16 · see citing works
Moore, S., Fang, E., Nguyen, H. A., & Stamper, J. C. (2023) · ACM Conference on Learning @ Scale (L@S) · doi:10.1145/3573051.3593396 · Cited by 9 · see citing works
Arabic Question Generation Using Transformers
Alajmi, A., Altabaa, H., Abed, S., & Ahmad, I. (2024) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3701559 · Cited by 2 · see citing works
ESQAD: A curriculum-aligned dataset for question answer generation in Spanish
Badenes-Olmedo, C., Eyzaguirre-Barreda, P., Chu-Artzt, N., & Gayoso-Cabada, J. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.115255 · Cited by 1 · see citing works
Text Summarization of Batak Toba Language Using Bidirectional Auto-Regressive Transformers Model
Samosir, N. S., Mawardi, V. C., & Batumalay, M. (2024) · International Conference on Information and Communications Technology (ICOIACT) · doi:10.1109/icoiact64819.2024.10913050 · Cited by 1 · see citing works
LLM Enabled Phoneme-Aware Pronunciation Feedback System for Rural English Learners
Reddy, K. A., Reddy, P. A., & Anand, S. (2026) · International Conference on Power, Control and Computing Technologies (ICPC2T) · doi:10.1109/icpc2t68221.2026.11646264
Adnan, M. A., Lhaksmana, K. M., & Ummah, I. (2026) · IEEE International Conference on Artificial Intelligence and Mechatronics Systems (AIMS) · doi:10.1109/aims71270.2026.11712733
- Authors
- Ji, T., Lyu, C., Jones, G., Zhou, L., & Graham, Y.
- Affiliations
- Dublin City University (IE)
- Trinity College Dublin (IE)
- Corresponding author
- Lyu, Chenyang
- Graham, Yvette
- Venue
- Entropy
- Publisher
- MDPI AG
- Published
- 2022-10-24
- Volume
- 24
- Issue
- 11
- Pages
- 1514
- ISSN
- 1099-4300 (ISSN-L)
- PMC
- PMC9689497
- OpenAlex
- W4307273670
- Cited by
- 12
- References
- 51
- Citations by year
- 2026: 3 · 2024: 3 · 2023: 6
- FWCI
- 0.74
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Entropy (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University) (cc-by)
- Funders
- SFI Research Centres Programme (13/RC/2106_P2, 13/RC/2106, 18/CRT/6183)
- Science Foundation Ireland through the SFI Centre for Research Training in Machine Learning (13/RC/2106_P2, 13/RC/2106, 18/CRT/6183)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Keywords
- question generation, cross-entropy, human judgment correlation, BERTScore, BLEU
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
