Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training, NAACL 2025
IHEval: Evaluating Language Models on Following the Instruction Hierarchy, NAACL 2025
Adaptive Preference Scaling for Reinforcement Learning with Human Feedback, NeurIPS 2024
Robust Reinforcement Learning from Corrupted Human Feedback, NeurIPS 2024
Data Diversity Matters for Robust Instruction Tuning, EMNLP 2024
BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering, EMNLP 2024
Large Language Models in the Clinic: A Comprehensive Benchmark, EMNLP 2024
Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs, ACL NLRSE Workshop 2024
Background
Research interests include generative AI, large language modeling, deep learning, and open-source software for data analysis. Was a principle scientist at Amazon Generative Foundation Modeling Team, currently working at OpenAI.