About Me
I'm a researcher working at the intersection of technical AI safety and governance, with a special focus on legal alignment of AI agents and assessing compliance capabilities of AI. As we accelerate toward a potential intelligence explosion with AI, we need to ensure that these technologies are safe, lawful, and aligned with human values.
I'm extremely active in collaborating with fellow researchers from the AI, law, governance, and safety space. Currently, I'm working with Prof. Noam Kolt on the legal alignment of AI agents as part of my Pivotal Fellowship. Consequently, I'm also collaborating with Ben Brady and Cullen O'Keefe from the Institute for Law & AI on benchmarking the law-following capabilities of AI agents.
My work is often published at high-impact venues, including NeurIPS, ACL, EMNLP, ICML, and ICLR.
Before moving to the UK, I worked as a Senior NLP Researcher in the Human Language Technology Lab at National University in the Philippines.
News
- My ScrapeBench project has been accepted to NeurIPS 2026. My other co-authored papers, GlobalPIQA and Jarvis-Bench, have also been accepted. Preprints soon!
- Two papers, ComplexityMT and a position paper on rethinking compliance in LLMs, have been accepted to EMNLP 2026!
- I reached 2,000 citations in Google Scholar.
- Invited panel talk at the Workshop on Law-Following AI hosted by the Institute for Law & AI, Centre for the Future of Intelligence in Jesus College, Cambridge.
- Dynamic Epistemic Fallback has been accepted to the ICML AI for Law (AI4Law) Workshop.
- Scaling Policy Reasoning Traces has been accepted to the ICML Technical AI Governance Research (TAIGR) Workshop.
- Our Humanity's Last Exam Benchmark is now published in Nature.
- I'm thrilled to have been awarded the Pivotal Research Fellowship. I will work with Prof. Noam Kolt and will be based at the London Initiative for Safe AI (LISA) Office.
Selected Publications
Please check my Google Scholar for the complete list.
2026
Experience
- 2026
(ongoing) - Technical AI Governance FellowPivotal Research, London Initiative for Safe AI
Working on legal alignment of frontier AI agents under Noam Kolt (GOAL). Also collaborating with Ben Brady and Cullen O'Keefe at the Institute for Law & AI on developing benchmarks for law-following AI. This is a non-internship research program.
- 2018
(on study leave) - Senior NLP ResearcherNational University Philippines
Managed the NU HLT Lab, which housed undergraduate students working on NLP projects, and collaborated with industry partners on NLP use cases in education and food nutrition.
- 2017–2018
- Research FellowNational University Philippines and Philippine-California Advanced Research Institutes
Worked on the E-Participation 2.0: Connective Diverse Philippine Populations for Disaster Risk Management with a Toolkit Integrating Text and Speech Analytics, a two-year collaborative project with the University of California, Berkeley.
Education
- 2022–2026
(expected) - Ph.D. in Accountable, Responsible, and Transparent AI (ART-AI)University of Bath, UK
Working on the compliance dynamics and alignment of LLMs with multi-domain policies and regulations. Supervised by Dr. Harish Tayyar Madabushi and Dr. Gail Forey.
Supported by UKRI Doctoral Fellowship, Pivotal Research Fellowship, and the National University Study Grant Program.
- 2018–2021
- M.S. in Computer ScienceDe La Salle University, Philippines
Conducted the most extensive set of explorations of linguistic features for machine learning-based Filipino readability classification under the guidance of Dr. Ethel Ong.
Supported by the DLSU St. La Salle Scholarship and the National University Study Grant Program.
Awards & Recognition
- 2025
- Pivotal Research FellowshipPivotal Research and London Initiative for Safe AI
- 2024
- Doctoral Recognition AwardUniversity of Bath
- 2023
- Researcher of the Year AwardNational University Philippines
- 2026, 2024, 2023
- Outstanding Reviewer AwardICML (2026, 2024), ACL (2023)
- 2022–2026
- UKRI CDT Doctoral FellowshipUK Research and Innovation
- 2021
- Google AI and Tensorflow GrantGoogle
Media Presence
- Newsweek
Quoted in a Newsweek article on what OpenAI's agent swarm hacking means for AI safety
- AIHub
Interview with AIHub on my PhD research at AAAI 2025.
- New Scientist
Interview with Chris Stokel-Walker for The New Scientist on the future evaluations of AGI models.
- PEP Magazine
Interview with PEP Magazine on the dangers of privacy of deepfakes.
- The New York Times
Our Humanity's Last Exam (HLE) benchmark featured on The New York Times.
Socials