Research
Systems
Language models for messy evidence
Language models for messy evidence
I build research workflows that turn survey responses, conflict reports, and county-scale data into inspectable evidence. The work sits between machine learning and domain research: multi-agent thematic analysis, domain-adapted NLP, multilingual question answering, and spatial modeling.
Role
AI/ML Researcher
Research Surface
Text, conflict data, counties
Stack
Python, LangGraph, Transformers
Output
Systems, analysis, papers
The research stack includes a LangGraph pipeline that reduced expert analysis time by 10x, ConfliBERT adaptation that reached 90 F1 on conflict-text classification, Spanish and Arabic extensions for cross-lingual QA, and a county-disparities study across 34 outcomes and 3100+ counties. Two papers from this work are under review.
Study Area
Applied AI Research
Publication Status
Two papers under review
Primary Focus
Research infrastructure
Program Fit
Interdisciplinary systems