% Key papers for Explanatory and multiple-choice QA benchmarks (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2020_piqa_102929,
  title = {{PIQA: Reasoning about Physical Commonsense in Natural Language}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6239},
}

@inproceedings{iclr2019_wizard_29125,
  title = {{Wizard of Wikipedia: Knowledge-Powered Conversational Agents}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/739},
}

@inproceedings{aaai2020_winogrande_103089,
  title = {{WinoGrande: An Adversarial Winograd Schema Challenge at Scale}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6399},
}

@inproceedings{aaai2018_a_105917,
  title = {{A Knowledge-Grounded Neural Conversation Model}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11977},
}

@inproceedings{aaai2020_qasc_103009,
  title = {{QASC: A Dataset for Question Answering via Sentence Composition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6319},
}

@inproceedings{aaai2021_retrospective_1275,
  title = {{Retrospective Reader for Machine Reading Comprehension}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/14506-retrospective-reader-for-machine-reading-comprehension/},
}

@inproceedings{aaai2018_a_105896,
  title = {{A Deep Generative Framework for Paraphrase Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11956},
}

@inproceedings{aaai2018_complex_100585,
  title = {{Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11332},
}

@inproceedings{aaai2017_building_104604,
  title = {{Building Task-Oriented Dialogue Systems for Online Shopping}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11182},
}

@inproceedings{aaai2016_combining_105171,
  title = {{Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10325},
}

@inproceedings{aaai2020_evaluating_103213,
  title = {{Evaluating Commonsense in Pre-Trained Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6523},
}

@inproceedings{iclr2018_ask_28575,
  title = {{Ask the Right Questions: Active Question Reformulation with Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/107},
}

@inproceedings{aaai2020_jec_103209,
  title = {{JEC-QA: A Legal-Domain Question Answering Dataset}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6519},
}

@inproceedings{aaai2020_select_103131,
  title = {{Select, Answer and Explain: Interpretable Multi-Hop Reading Comprehension over Multiple Documents}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6441},
}

@inproceedings{aaai2020_dcmn_103192,
  title = {{DCMN+: Dual Co-Matching Network for Multi-Choice Reading Comprehension}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6502},
}

@inproceedings{aaai2016_addressing_105200,
  title = {{Addressing a Question Answering Challenge by Combining Statistical Methods with Inductive Rule Learning and Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10354},
}

@inproceedings{iclr2023_generate_32933,
  title = {{Generate rather than Retrieve: Large Language Models are Strong Context Generators}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/12027},
}

@inproceedings{aaai2018_end_105919,
  title = {{End-to-End Quantum-like Language Models with Application to Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11979},
}

@inproceedings{iclr2020_low_29776,
  title = {{Low-Resource Knowledge-Grounded Dialogue Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rJeIcTNtvS},
}

@inproceedings{neurips2016_dialog_55678,
  title = {{Dialog-based Language Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7317},
}

@inproceedings{aaai2024_flexkbqa_6026,
  title = {{FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29823},
}

@inproceedings{cvpr2024_openeqa_24378,
  title = {{OpenEQA: Embodied Question Answering in the Era of Foundation Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29575},
}

@inproceedings{aaai2024_cyberq_5542,
  title = {{CyberQ: Generating Questions and Answers for Cybersecurity Education Using Knowledge Graph-Augmented LLMs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30362},
}

@inproceedings{aaai2024_improving_6288,
  title = {{Improving Automatic VQA Evaluation Using Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28212},
}

@inproceedings{aaai2024_xiezhi_7835,
  title = {{Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29767},
}

@inproceedings{aaai2025_citations_8418,
  title = {{Citations and Trust in LLM Generated Responses}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34550},
}

@inproceedings{aaai2024_enhancing_5861,
  title = {{Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30370},
}

@inproceedings{aaai2024_retllm_7126,
  title = {{RetLLM-E: Retrieval-Prompt Strategy for Question-Answering on Student Discussion Forums}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30368},
}

@inproceedings{neurips2024_mediq_72508,
  title = {{MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94856},
}

@inproceedings{aaai2024_improving_6308,
  title = {{Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29881},
}

@inproceedings{aaai2024_reverse_7144,
  title = {{Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thought}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29942},
}

@inproceedings{cvpr2024_cog_22982,
  title = {{CoG-DQA: Chain-of-Guiding Learning with Large Language Models for Diagram Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31099},
}

@inproceedings{neurips2024_on_71907,
  title = {{On scalable oversight with weak LLMs judging strong LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95397},
}

@inproceedings{aaai2024_improving_6302,
  title = {{Improving Open-Domain Dialogue Response Generation with Multi-Source Multilingual Commonsense Knowledge}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29894},
}

@inproceedings{aaai2025_knowledge_9652,
  title = {{Knowledge Tagging with Large Language Model Based Multi-Agent System}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35141},
}

@inproceedings{aaai2025_qgen_10407,
  title = {{QGen Studio: An Adaptive Question-Answer Generation, Training and Evaluation Platform}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35362},
}

@inproceedings{iclr2024_achieving_34441,
  title = {{Achieving Human Parity in Content-Grounded Datasets Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18634},
}

@inproceedings{aaai2024_corecode_5356,
  title = {{CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29861},
}

@inproceedings{iclr2026_counselbench_84934,
  title = {{CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=8MBYRZHVWT},
}

@inproceedings{neurips2024_subjective_73205,
  title = {{SubjECTive-QA: Measuring Subjectivity in Earnings Call Transcripts' QA Through Six-Dimensional Feature Analysis}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://openreview.net/forum?id=f5XZEROoGb},
}