Published 'Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration' at ACL 2024, awarded Area Chair Award (QA track) and Outstanding Paper Award
Published 'Resolving Knowledge Conflicts in Large Language Models' at COLM 2024
Published 'Teaching LLMs to Abstain across Languages via Multilingual Feedback' at EMNLP 2024
Published 'Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence' at ICML 2025
Published 'Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems' at NeurIPS 2025
Multiple preprints including 'Don't Throw Away Your Pretrained Model', 'ScienceMeter', 'Data Swarms', and 'When One LLM Drools, Multi-LLM Collaboration Rules'
Published 'Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media' in PNAS Nexus 2025