Glenn Matlin
PhD Student • Georgia Tech • MATS Scholar
I study how AI systems learn about humans from our data, how they generalize from patterns, and how to use those findings to improve capabilities and safety. My PhD research, RAPID-AI, focuses on reasoning, analysis, and planning for high-stakes decisions.
Currently a MATS Scholar working on AI safety policy.
RAPID-AI Research
T1: Grounded STS Evaluation
Building expert-level evaluations from authoritative sources — cited QAs and multi-step tasks that test knowledge, multi-hop reasoning, planning, and trade-off analysis across socio-technical domains.
T2: Training for Reasoning & Planning
Curated and synthetic data, supervised fine-tuning, and RL with structure-aware rewards. Developing methods that improve generalizable reasoning rather than domain memorization.
T3: Assurance & Interpretability
Cognitive-pattern analysis, mechanistic and behavioral probes, uncertainty signals, and constraint checks. Making model behavior legible and auditable for high-stakes use.
T4: Human-in-the-Loop Interaction
Interfaces that elicit justifications, capture counterfactuals, and support red-teaming of plans. Ensuring humans can trust and appropriately use LM recommendations.
Featured Work
Research
FLAME - Financial LLM Evaluation
A comprehensive framework for evaluating large language models on financial domain knowledge, reasoning, and compliance tasks.
Publication
UnfoldML @ NeurIPS 2022
Cost-aware and uncertainty-based framework for dynamic 2D prediction in multi-stage classification systems.
Let’s Connect
I’m always interested in discussing research collaborations, interesting problems, and new opportunities.