Senior Evaluation Specialist | Research Fellow
Lucas Sempé
Brazilian-Argentine policy researcher with over two decades of experience spanning grassroots programme delivery, senior government leadership, and academic research. As Director at Peru's Ministry of Education, managed a £2 billion budget covering results-based reforms, teacher policy, and school governance. Current research focuses on evidence-informed policymaking, AI/digital policy governance, health financing, and the use of large language models for research automation. Published in The Lancet, BMJ, Social Science & Medicine, and Review of Income and Wealth. Over £1.5 million in research funding secured as PI/co-PI.
Recent Posts
View all →
The Instruction Tuning Firewall
Mental health chatbots can drift toward dangerous validation while sounding perfectly appropriate. I built a monitoring system that detects persona drift in model activations—catching problems that even a fine-tuned DeBERTa misses, with a 2.6× advantage on crisis recognition. Validated by two clinical psychologists (ICC=0.716) and tested on naturalistic emotional support conversations.
When Algorithms Meet Warzones
A drone image classifier that can't distinguish combatants from farmers. A beneficiary targeting model trained on data from before the displacement. A chatbot collecting trauma narratives in a language it barely understands. These aren't hypotheticals—they're the edge cases where AI meets impact evaluation in fragile contexts.
The Capacity Gap
I scored 2,216 AI policy documents across 193 countries on implementation capacity. The headline isn't that rich countries do better—it's that the gap nearly vanishes once you account for documentation quality. The real story is what's happening within income groups.
Talking to Your Evidence Base
What if you could ask your research library a question out loud and get a spoken answer grounded in actual studies? A retrieval-augmented system with voice interface makes research synthesis conversational.