Scholar
Shannon Zejiang Shen
Google Scholar ID: V0K3gs0AAAAJ
Massachusetts Institute of Technology
Citations & Impact
Citations
1,388
H-index
18
i10-index
22
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published several papers, such as 'Co-LLM: Training LLMs to Decode Collaboratively', 'Reduce Hallucination in Patient Summarization', 'Verifiable Text Generation via Symbolic References', etc. Also gave numerous academic talks and lectures, e.g., 'Rethinking the Design and Evaluation of Human and LLM Collaboration' at the Stanford HCI Group Lunch Seminar.
Research Experience
- Involved in multiple research projects, including Co-LLM: Training LLMs to Decode Collaboratively, Reduce Hallucination in Patient Summarization, Verifiable Text Generation via Symbolic References, Chapyter: LLM coding assistant in JupyterLab, and Real-world Legal Summaries at Multiple Granularities.
Education
- Currently a fourth-year PhD student in the Computer Science department at MIT, advised by David Sontag.
Background
- Research interests: collaboration between humans and AI (especially large language models) for expert tasks. Research involves developing novel NLP models and suitable interactions/interfaces to tackle challenging HAI problems like model hallucination and generation verification, and support expert tasks such as programming, doctors' writing, and legal summarization.
Miscellany
- Personal interests include visual design in scholarly communication.
Co-authors