Research
Published research, a bachelor's thesis, and the academic side of the work.
Peer-Reviewed Publication
Co-authored a peer-reviewed paper examining the use of Large Language Models in research and data analysis. The work has been cited over 170 times (55+ on Scopus), contributing to the academic discourse on responsible AI adoption in scientific workflows.
Impact: 170+ citations, 55+ on Scopus
Bachelor's Thesis
A novel shift-left approach to LLM hallucination mitigation. Introduced a user-sided hallucination taxonomy (Prompt Risk vs. Meta Risk), the Prompt Risk Density (PRD) metric for quantifying hallucination potential, and a multi-agent pipeline (Analyzer, Initiator, Conversation, Preparator) for iterative prompt refinement with human-in-the-loop validation.
Impact: Contribution to trustworthy AI in high-stakes domains (law, healthcare, finance)
Open the full PDF in a new tab or download it directly.
Quick copy blocks for talks, proposals, and project intros.
Thesis one-liner
Echo introduces a shift-left method to reduce LLM hallucination potential at prompt time, before generation starts.
PRD metric
Prompt Risk Density (PRD) is a weighted score that quantifies ambiguity and structural prompt risk likely to trigger hallucinations.
Practice bridge
Research helps me design production systems that fail safely, with explicit guardrails, observability, and predictable behavior under uncertainty.
I find it useful to stay close to the research side. Not every paper translates to production, but understanding why something works makes building with it much more reliable. My academic work has mostly shaped how I think about failure modes and edge cases.
This website can use privacy-friendly analytics to improve content quality. No advertising cookies are used.
You can change this anytime in the privacy page. Read more in Privacy Policy.