Bingsheng Arthur Yao
I am a postdoc associate at Northeastern University (PI: Prof. Dakuo Wang). My research at the intersection of NLP and HCI focuses on the responsible design of Human-Centered NLP systems to support collaborative work among stakeholders in various scenarios, including medical, healthcare, and education. Recently, my research interest extends to leveraging and enhancing LLM Role-Playing Agents to simulate human behaviors.
Research
In medical and healthcare, my research focuses on understanding the needs and challenges encountered by care providers, caregivers, and patients in different clinical scenarios, followed by the human-centered design of AI-assisted Clinical Decision Support System (CDSS) and Remote Patient Monitoring (RPM) systems. Prior work include: early diagnosis of sepsis [CHI ‘24]; RPM for older adults [IMWUT ‘24a], post-surgery care of GI cancer patients [1] [2], cardiotoxicity of cancer patients [3] [CHI ‘25a], and mental health of youth concussion patients [4].
My research extends to support parents’ need in interactive storytelling for children education, including needs solicitations [CSCW ‘24]; experts-annotated datasets, such as FairytaleQA [ACL ‘22a] and StorySparkQA [EMNLP ‘24]; QA-pair generation pipelines [ACL ‘22b]; and human-centered interactive storytelling systems [CHI ‘22] [CHI ‘25b].
Following my doctoral thesis, I am also devoted to develop efficient domain-adaptation and personalization methodologies for NLP models, which include: Active Learning for compact models [EMNLP ‘23]; In-Context Sampling [NAACL ‘24] and Knowledge Graph-RAG [CHI ‘25b] for LLMs; Supervised fine-tuning for domain-specific LLMs, such as Mental-LLM [IMWUT ‘24b]; and LLM Role-Playing Agents [5].
Education
- Ph.D. in Computer Science
Rensselaer Polytechnic Institute (Advisor. Prof. Jim Hendler) - M.S. in Information Technology
Rensselaer Polytechnic Institute - B.S. in Computer Engineering
Rensselaer Polytechnic Institute
Note
Please refer to my Google Scholar page for the most up-to-date publication record.
The best way to reach out is through emails: b [dot] yao [at] northeastern [dot] edu.
News
| 2025.02 | Co-first authored paper Survey of LLM Role-Playing Agent Evaluation is now publically available on arXiv |
|---|---|
| 2025.01 | Five papers were accepted to CHI 2025. Thanks for the hard working by collaborators and mentees! |
| 2024.10 | Our paper StorySparkQA Dataset with Real-World Knowledge for Children Education was accepted to EMNLP 2024 |
| 2024.09 | Our paper Secret Use of Large Language Models was accepted to CSCW 2025 |
| 2024.08 | Our paper Parent’s Needs for Preschoolers’ Storytelling and Reading Activities was accepted to CSCW 2024 |
| 2024.07 | Our paper Early Sepsis Prediction with Uncertainty Quantification and Active Sensing was accepted to KDD 2024 |
| 2024.04 | Our paper LLM-based Voice Assistant for Asynchronous Older Adults-Care Provider Communication and Mental-LLM were 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 associate! |
| 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 |
| 2023.10 | 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 |
Travels
| 2025.04.30 | Yokohama, JP CHI 2025 |
|---|
Service
Area Chair
ACL ARR (Since Jun. ‘24)
CHI ‘25, CSCW ‘25
Organizing Committee
CHI ‘24 Special Interest Group - Human-Centered Privacy Research in the Age of Large Language Models
CSCW ‘24 Workshop - Challenges and Opportunities of LLM-Based Synthetic Personae and Data in HCI
Reviewer
Conferences: ACL ARR (Aug. ‘23, Oct. ‘23, Dec. ‘23), EMNLP ‘23, NAACL ‘24, CHI ‘24, IUI ‘24, IMWUT ‘24
Journals: Natural Human Behavior, IJHCI, IJHCS