Research ยท Vela Research and the University of Oxford
Research
The papers behind Think, Reason, Learn and its first model, FounderBrain. Each method keeps its reasoning in a form a person can read and check.
The model behind FounderBrain
How 100 fixed yes or no questions about each answer, and a psychometric model, turn a meeting transcript into four speaking styles compared with 773 public founder interviews.
Accepted at the NeurIPS 2026 TAE (Trust-AI-Eval) workshop. The paper is coming soon.
VCBench: Benchmarking LLMs in Venture Capital
A benchmark for predicting founder success from anonymised founder profiles, with a public leaderboard of models and people.
Chen, Ternasky, Kwesi, Griffin, Yin, Salifu, Amoaba, Mu, Alican and Ihlamur
Random Rule Forest: Interpretable Ensembles of LLM-Generated Questions for Predicting Startup Success
A language model writes many yes or no questions about each case, and a transparent ensemble combines the answers into one prediction.
Griffin, Yin, Vidaurre, Koyluoglu, Ternasky, Alican and Ihlamur
Reasoned Rule Mining: Calibrated LLM Classification for Quant VC
Turns a language model's reasoning into rules with calibrated probabilities, so a prediction comes with a confidence you can trust, and runs the costly model only when the cheap checks are unsure.
Preuveneers and Ihlamur
Policy Induction: Predicting Startup Success via Explainable Memory-Augmented In-Context Learning
Learns short policies from examples, written plainly enough for a person to check, which a model then applies to new cases.
Mu, Ternasky, Alican and Ihlamur
GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees
Decision trees whose questions a language model writes, so every branch is a question a person can read.
Xiong, Ihlamur, Alican and Yin
Work with us
Questions about the research, or ideas for a collaboration.