# A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC

arXiv: https://arxiv.org/abs/1809.10735 · HTML: https://mlsanity.com/paper/1809.10735/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2018.

## Built on by (most cited first, 22 of 22)

- [DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering](https://mlsanity.com/paper/2211.05655/) (2022)
- [QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension](https://mlsanity.com/paper/2107.12708/) (2021)
- [Context-faithful Prompting for Large Language Models](https://mlsanity.com/paper/2303.11315/) (2023)
- [An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics](https://mlsanity.com/paper/2207.00939/) (2022)
- [Neural Approaches to Conversational Information Retrieval](https://mlsanity.com/paper/2201.05176/) (2022)
- [Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering](https://mlsanity.com/paper/2101.00391/) (2021)
- [Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review](https://mlsanity.com/paper/2309.06055/) (2023)
- [A Survey of Recent Backdoor Attacks and Defenses in Large Language Models](https://mlsanity.com/paper/2406.06852/) (2024)
- [Conversational Question Answering: A Survey](https://mlsanity.com/paper/2106.00874/) (2021)
- [How well do you know your summarization datasets?](https://mlsanity.com/paper/2106.11388/) (2021)
- [Learning Disentangled Representations of Negation and Uncertainty](https://mlsanity.com/paper/2204.00511/) (2022)
- [Learning to Select the Relevant History Turns in Conversational Question Answering](https://mlsanity.com/paper/2308.02294/) (2023)
- [Does Entity Abstraction Help Generative Transformers Reason?](https://mlsanity.com/paper/2201.01787/) (2022)
- [FedSEA-LLaMA: A Secure, Efficient and Adaptive Federated Splitting Framework for Large Language Models](https://mlsanity.com/paper/2505.15683/) (2025)
- [A Survey of the State-of-the-Art in Conversational Question Answering Systems](https://mlsanity.com/paper/2509.05716/) (2025)
- [Explainable Semantic Text Relations: A Question-Answering Framework for Comparing Document Content](https://mlsanity.com/paper/2509.08304/) (2025)
- [SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2512.04868/) (2025)
- [TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins](https://mlsanity.com/paper/2606.17660/) (2026)
- [How to Build Robust FAQ Chatbot with Controllable Question Generator?](https://mlsanity.com/paper/2112.03007/) (2021)
- [Combining EEG and NLP Features for Predicting Students' Lecture Comprehension using Ensemble Classification](https://mlsanity.com/paper/2311.11088/) (2023)
- [Answerability in Retrieval-Augmented Open-Domain Question Answering](https://mlsanity.com/paper/2403.01461/) (2024)
- [From the Rock Floor to the Cloud: A Systematic Survey of State-of-the-Art NLP in Battery Life Cycle](https://mlsanity.com/paper/2510.27369/) (2025)

## Abstract (arXiv)

We compare three new datasets for question answering: SQuAD 2.0, QuAC, and CoQA, along several of their new features: (1) unanswerable questions, (2) multi-turn interactions, and (3) abstractive answers. We show that the datasets provide complementary coverage of the first two aspects, but weak coverage of the third. Because of the datasets' structural similarity, a single extractive model can be easily adapted to any of the datasets and we show improved baseline results on both SQuAD 2.0 and CoQA. Despite the similarity, models trained on one dataset are ineffective on another dataset, but we find moderate performance improvement through pretraining. To encourage cross-evaluation, we release code for conversion between datasets at https://github.com/my89/co-squac .