Think, Reason, Learn

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.

  1. 2026NeurIPS workshop

    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.

  2. 2025arXiv preprint

    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

  3. 2025arXiv preprint

    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

  4. 2025IEEE SecureFinAI

    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

  5. 2025IEEE SecureFinAI

    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

  6. 2024arXiv preprint

    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.

research@vela.partners