Posts by Collection

Socratic Tutoring LLM via Multi-Stage Policy Optimization

Fine-tuning open-source LLMs (SFT, Offline DPO, Online GRPO) to align them as Socratic tutors that guide students without prematurely leaking answers.

eGPT

An internal RAG chatbot powered by a local LLM for confidential data handling, designed to assist employees with personalized services.

Vinsight

Won the User Experience Award at the Vakıfbank Hack to the Future Hackathon. A hub for organizational memory with local document and voice memo querying.

Cherry Merchant Finder App

Won the 2025 Cherry New Grad Hackathon. An interactive map-based interface to help consumers find merchants offering Cherry’s services.

Reinforcement Learning Methods Research in Low Resource Languages

Applied RLHF techniques (GRPO, PPO) to optimize LLMs for low-resource languages, outperforming SFT and standard baselines. Ranked 4th/35.

OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models

Published in ArXiv Preprint, 2025

A comprehensive ethical evaluation framework for open-source generative LLMs, assessing performance in Turkish and English.

Recommended citation: Yıldırım Özen, Erinç Çetin, Kaan Engür, Elif Naz Demiryılmaz, Çağrı Toraman. (2025). "OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models." ArXiv Preprint.
Download Paper

Teaching Assistant - MAS AID Program

Graduate program, ETH Zurich, MAS AID Program, 2025

Teaching Assistant for the ETH Zurich MAS in Applied Information and Data Science (AID) program, which is designed to enhance managers’ technical understanding of machine learning.