Hi! I'm Lj V. Miranda, and welcome to my website!
I'm a PhD student at the University of Cambridge, researching multilingual and equitable NLP, where I'm advised by Anna Korhonen. In the past, I've worked as an engineer, consultant, and researcher (see my CV), mostly in the fields of NLP and AI.
I'm broadly interested in data-centric approaches to building language technologies at scale. I also have a special interest in improving the state of Filipino NLP. I'm happy to discuss research and collaborate, so feel free to reach out and chat!
Recent posts
-
The Filipino qualities we need to build world-class language technologies
I was invited to give a talk at Analytics & AI Association of the Philippines (AAP) on FilBench, and in general, building Filipino LLMs. This blog post covers some of my thoughts on this topic.
-
Reflections of a Pinoy applying to CS PhD programs abroad
A long reflection about my journey from industry to grad school applications—spanning multiple countries, jobs, and experiences. This is not an advise post, but I hope you'll find something valuable along the way.
-
Introducing FilBench: An Open LLM Evaluation Suite for Filipino
This National Language Month, I'm proud to introduce FilBench, a big step forward in Filipino NLP evaluation. This work was also accepted at EMNLP Main! Read to learn more about this project.
What's new?
Jun 2026: I am part of the Scientific Committee of the Philippine Team for the International Olympiad for Artificial Intelligence. I also gave a training lecture for NLP (see lecture materials). Go Team PH!
May 2026: Gave a talk at the Analytics and AI Association of the Philippines about FilBench and on what it takes to build Filipino-centric LLMs (slides). Here’s some notes from my talk.
May 2026: Proud to release our survey on multilingual edge models (check the website!). If you know me, I care a lot about AI in the Global South, I’d like to continue doing these types of sociotechnical research, so reach out if you wanna chat!
Apr 2026: Sharing my first PhD work, Polyglot Teachers! Here, I studied what makes a good teacher model for generating multilingual data. I’m excited to continue this research agenda on multilingual synthetic data generation!
Dec 2025: So excited to see the release of OLMo 3! My contribution was on creating the tool-use SFT mix during my last few months as a pre-doc. My experience here made me excited in agentic tool-use!
Oct 2025: I’m starting my PhD at the University of Cambridge - Language Technology Lab and will be advised by Anna Korhonen.