Scholar
Chao Shang
Google Scholar ID: 3-FvYxAAAAAJ
Amazon AWS AI
Citations & Impact
Citations
2,170
H-index
13
i10-index
17
Publications
20
Co-authors
15
list available
Publications
Resume (English only)
Academic Achievements
- Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate, arXiv, 2025
- STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents, arXiv, 2025
- Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models, ACL Findings, 2025
- From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification, NAACL Findings, 2025
- Diable: Efficient Dialogue State Tracking as Operations on Tables, ACL 2023 (Findings)
- Automatic depression screening using social interaction data on smartphones, Smart Health, 2022
- Variance of the Gradient Also Matters: Privacy Leakage from Gradients, IJCNN, 2022
- Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphs, ACL, 2022
- TAG: Gradient Attack on Transformer-based Language Models, EMNLP 2021 (Findings)
- Open Temporal Relation Extraction for Question Answering, AKBC, 2021
Research Experience
- 06/2022–Present: Senior Applied Scientist at Amazon AWS AI – developing high-performance LLMs and customized solutions for Amazon Bedrock; building safeguards for generative AI applications via Amazon Bedrock Guardrails
- 09/2020–05/2022: Research Scientist at JD AI Research, JD.COM Silicon Valley Research Center, mentored by Dr. Jing Huang
- 01/2020–06/2020: Research Intern at MIT-IBM Watson AI Lab, IBM Research, mentored by Dr. Jie Chen
- 05/2019–09/2019: Research Intern at IBM Thomas J. Watson Research Center, IBM Research, Knowledge Induction Team
- 05/2018–09/2018: Research Intern at JD AI Research, JD.COM Silicon Valley Research Center, SAIL-JD Knowledge Graph Research Program
