Hi, I'm Melanie

An emerging researcher across AI safety and AI governance, asking what better governance could look like for countries that didn't set the rules of the game.

—Ideas—Projects—Library—About

Working Notes

01
Apr 2026NLP

Explainable Vietnamese Legal Relation Classification

Fine-tuning PhoBERT on Vietnamese legal texts and testing whether predictions stay stable under wording perturbations.

→
02
Mar 2026Project

Rubric-based Grading Tool

A benchmark-oriented grading workflow for reasoning-heavy exam questions using Gemini, prompt experiments, and score-alignment metrics.

→
03
Mar 2026NLP

Why evaluation is becoming my favorite part of NLP

A reflection on ambiguity, grading, judgment, and why evaluation feels like one of the most intellectually alive parts of language models.

→
04
Dec 2025AI Safety

coherenteyes: Fake News Detection

A SHAP-based interpretable fake news detection system, framed through AI Safety

→
05
Dec 2025Game Theory

Two Equilibria, One Dilemma

Signaling, coordination, and digital authoritarianism through the contrast between Singapore and China.

→