Bingsheng "Arthur" Yao


I am a Postdoc researcher at Northeastern University (PI: Prof. Dakuo Wang). My research lies at the intersection of NLP and HCI. Before joining Prof. Dakuo’s group, I got Ph.D. from Rensselaer Polytechnic Institute (Advisor: Prof. Jim Hendler). My dissertation focuses on enhancing machine reasoning via Active Learning (AL) with human rationales – I propose a novel AL architecture with a diversity-based sampling strategy that generates and benefits from natural language explanations for data sampling and prediction (AL Architecture@EMNLP23, Human Rationale Evaluation@ACL23)

I strive to enhance human-AI collaborative workflow with NLP system in real-world, domain-specific scenarios. To list a few:

My research interests also extend to exploring efficient development and utilization of NLP models, including

I have served on program committees for various top conferences and journals:
EMNLP 23, NAACL 24, ACL ARR (from Aug23), CHI 24, IUI 24, IMWUT 24, IJHCS


2024.04 Our paper LLM-based Voice Assistant for Remote Communication between Older Adults and Care Providers was accepted to IMWUT 2024
2024.03 First-authored paper In-Context Sampling Strategy for Reliable LLM Prompting was accepted to NAACL 2024 Findings
2024.03 Guest talk at USC titled “Bridging AI Research and Real-world Scenarios”. Thanks Prof. Yao Du for the invitation!
2024.02 I am joining Prof. Dakuo Wang’s Human-Centered AI Lab at Northeastern University as a Postdoc researcher!
2024.01 Two of our papers, Human-AI Collaboration in Sepsis Diagnosis and User’s Sensitive Disclosure with LLM were accepted to CHI 2024
2024.01 I passed the Ph.D. dissertation defense. My deepest gratitude to all those who supported and helped me, especially Prof. Jim Hendler and Prof. Dakuo Wang
2023.12 Our paper Mental-LLM was accepted to IMWUT 2024
2023.10 Our paper, Discourse Framework for Science Journalism, was accepted to EMNLP 2023, and another first-authored paper, Active Learning Empowered by Natural Language Explanations, was accepted to EMNLP 2023 Findings
2023.07 First-authored paper Objective Evaluation of Human Explanations was accepted to ACL 2023 for Oral Presentation
2022.05 Two first-authored papers, QA-Pair Generation for Story Books and FairytaleQA Dataset were accepted to ACL 2022
2022.04 Our paper StoryBuddy was accepted to CHI 2022
2021.09 Our paper Narrative Open-Domain QA Techniques was accepted to TACL (2021) 9
2020.03 Our paper Trust in AutoML was accepted to IUI 2020



  1. Exploring Parent’s Needs for Children-Centered AI to Support Preschoolers’ Storytelling and Reading Activities
    Yuling Sun, Jiali Liu, Bingsheng Yao , Jiaju Chen, Dakuo Wang, and 4 more authors
    arXiv preprint arXiv:2401.13804, 2024
  2. Who Changed the Destiny of Rural Students, and How?: Unpacking ICT-Mediated Remote Education in Rural China
    Yuling Sun, Xiuqi Zhu, Xiaomu Zhou, Bingsheng Yao , Kai Zhang, and 3 more authors
    arXiv preprint arXiv:2401.13799, 2024


  1. More Samples or More Prompt Inputs? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineering
    Bingsheng Yao , Guiming Chen, Ruishi Zou, Yuxuan Lu, Jiachen Li, and 4 more authors
    arXiv preprint arXiv:2311.09782, 2023
  2. Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks
    Yuxuan Lu, Bingsheng Yao , Shao Zhang, Yun Wang, Peng Zhang, and 3 more authors
    arXiv preprint arXiv:2311.09825, 2023
  3. FairytaleCQA: Integrating a Commonsense Knowledge Graph into Children’s Storybook Narratives
    Jiaju Chen, Yuxuan Lu, Shao Zhang, Bingsheng Yao , Yuanzhe Dong, and 5 more authors
    arXiv preprint arXiv:2311.09756, 2023
  4. " Mango Mango, How to Let The Lettuce Dry Without A Spinner?”: Exploring User Perceptions of Using An LLM-Based Conversational Assistant Toward Cooking Partner
    Szeyi Chan, Jiachen Li, Bingsheng Yao , Amama Mahmood, Chien-Ming Huang, and 3 more authors
    arXiv preprint arXiv:2310.05853, 2023
  5. LLM-Powered Conversational Voice Assistants: Interaction Patterns, Opportunities, Challenges, and Design Guidelines
    Amama Mahmood, Junxiang Wang, Bingsheng YaoDakuo Wang, and Chien-Ming Huang
    arXiv preprint arXiv:2309.13879, 2023
  6. Talk2Care: Facilitating Asynchronous Patient-Provider Communication with Large-Language-Model
    Ziqi Yang, Xuhai Xu, Bingsheng Yao , Shao Zhang, Ethan Rogers, and 4 more authors
    arXiv preprint arXiv:2309.09357, 2023
  7. " It’s a Fair Game”, or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents
    Zhiping Zhang, Michelle Jia, Bingsheng Yao , Sauvik Das, Ada Lerner, and 3 more authors
    arXiv preprint arXiv:2309.11653, 2023
  8. Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosis
    Shao Zhang, Jianing Yu, Xuhai Xu, Changchang Yin, Yuxuan Lu, and 6 more authors
    arXiv preprint arXiv:2309.12368, 2023
  9. Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data
    Xuhai Xu, Bingsheng Yao , Yuanzhe Dong, Saadia Gabriel, Hong Yu, and 4 more authors
    arXiv preprint arXiv:2307.14385, 2023
  10. Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture
    Bingsheng YaoIshan JindalLucian PopaYannis Katsis, Sayan Ghosh, and 6 more authors
    In Findings of the Association for Computational Linguistics: EMNLP 2023, Dec 2023
  11. Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations
    Bingsheng YaoPrithviraj SenLucian PopaJames Hendler, and Dakuo Wang
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2023
  12. ‘Don’t Get Too Technical with Me’: A Discourse Structure-Based Framework for Automatic Science Journalism
    Ronald Cardenas, Bingsheng YaoDakuo Wang, and Yufang Hou
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023


  1. It is AI’s Turn to Ask Humans a Question: Question-Answer Pair Generation for Children’s Story Books
    Bingsheng Yao*Dakuo Wang*Tongshuang Wu, Zheng Zhang, Toby Li, and 2 more authors
    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), May 2022
  2. Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension
    Ying Xu*Dakuo Wang*Mo Yu*, Daniel Ritchie*, Bingsheng Yao* , and 13 more authors
    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), May 2022
  3. StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement
    Zheng Zhang*, Ying Xu*, Yanhao Wang, Bingsheng Yao , Daniel Ritchie, and 4 more authors
    In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, May 2022
  4. Nece: Narrative Event Chain Extraction Toolkit
    Guangxuan Xu*, Paulina Toro Isaza*, Moshi Li*, Akintoye Oloko, Bingsheng Yao , and 5 more authors
    arXiv preprint arXiv:2208.08063, May 2022
  5. GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
    Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, and 72 more authors
    In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Dec 2022
  6. A Corpus for Commonsense Inference in Story Cloze Test
    Bingsheng Yao , Ethan Joseph, Julian Lioanag, and Mei Si
    In Proceedings of the Thirteenth Language Resources and Evaluation Conference, Jun 2022
  7. Efficient Long Sequence Encoding via Synchronization
    Xiangyang MouMo YuBingsheng Yao , and Lifu Huang
    arXiv preprint arXiv:2203.07644, Jun 2022


  1. Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study
    Xiangyang Mou*, Chenghao Yang*, Mo Yu*Bingsheng Yao , Xiaoxiao Guo, and 2 more authors
    Transactions of the Association for Computational Linguistics, Jun 2021
  2. Building a Storytelling Conversational Agent Through Parent-AI Collaboration
    Zheng Zhang*, Ying Xu*, Yanhao Wang, Tongshuang WuBingsheng Yao , and 4 more authors
    Jun 2021


  1. Frustratingly Hard Evidence Retrieval For QA Over Books
    Xiangyang MouMo YuBingsheng Yao , Chenghao Yang, Xiaoxiao Guo, and 2 more authors
    arXiv preprint arXiv:2007.09878, Jun 2020
  2. Trust in AutoML: Exploring Information Needs for Establishing Trust in Automated Machine Learning Systems
    Jaimie Drozdal, Justin Weisz, Dakuo Wang, Gaurav Dass, Bingsheng Yao , and 4 more authors
    In Proceedings of the 25th International Conference on Intelligent User Interfaces, Jun 2020