Trustworthy AI · NLP ETH Zürich × University of Zürich
AI systems that know when to be trusted.
I am a PhD student mining the uncertainty hidden inside large language models and exposing it for human supervision — so people can rely on AI where the stakes are highest, from climate science to law.
About
Research grounded in reliability, oversight, and high-impact AI use.
I am a dedicated AI researcher passionate about building trustworthy AI systems that can make the future better. I am currently pursuing my PhD (2023–2027, expected) under the joint supervision of Prof. Elliott Ash and Prof. Mrinmaya Sachan at ETH Zurich, and Prof. Markus Leippold at University of Zurich. I divide my time equally between both institutions.
These methods matter most where the stakes are high and people stay accountable for the answer — which is why I ground them in climate and law. From corporate climate disclosures to legal reasoning, an unverified claim can sway policy or judgment, so domain experts need to see exactly how far to trust a model. I like to aim high while keeping my feet firmly on the ground.
Research focus
From a model's hidden uncertainty to human oversight.
Mine uncertainty from the model
Extract reliable uncertainty signals from large language models — probing internal states, quantifying uncertainty without interrupting generation, and fine-tuning models to recognize the limits of what they know.
Expose it for human supervision
Turn that signal into oversight people can act on — external verifiers, edge-case discovery, faithful evidence-grounded answers, and the output formats, interfaces, and visualizations built for human and machine review.
Projects & community service
Open models, climate NLP, and research communities.
Community collaboration
Apertus: Democratizing Open and Compliant LLMs
Community collaboration on democratizing open and compliant LLMs for global language environments, with contributions to trustworthiness post-training.
Technical report →Community collaboration
When AI Benchmarks Plateau
Community collaboration accepted to ICML 2026 on benchmark saturation and how plateauing scores affect evaluation practice.
ICML 2026 →Workshop
ClimateNLP at ACL 2025
Organizing the second ClimateNLP workshop at ACL 2025, Vienna.
Workshop
ClimateNLP at ACL 2024
Organized the first ClimateNLP workshop at ACL 2024, Bangkok.
Publications
Selected research
Mining uncertainty from language models — and the verifiers, annotations, and interfaces that surface it for people.
ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
Reads the model's own internal states mid-reasoning to tell when an answer has settled, scaling test-time reasoning only as far as the model actually needs.
Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?
Tests whether reasoning lets a model recognize when a question is genuinely contested, instead of collapsing real human disagreement into one overconfident answer.
DIRAS: Efficient LLM Annotation of Document Relevance for Retrieval Augmented Generation
Trains small, cheap models to judge whether retrieved documents are truly relevant, giving RAG an external check on its evidence before the generator ever sees it.
Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification
Pairs human annotators with an LLM to surface the edge cases a classifier quietly gets wrong, pointing oversight straight at the model's blind spots.
Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering
Trains open QA specialists to answer strictly from the evidence they are given and resist being misled when it is noisy or missing — keeping every answer traceable to its source.
AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators
Cross-checks several LLM annotators against each other to reliably flag which sentences are checkable factual claims — the first filter any fact-verification pipeline needs.
Full publication list
Accepted In review / preprint
Education
Academic path
PhD @ ETH D-GESS
ETH Zürich & University of Zürich
MSc in Data Science & Machine Learning
University College London
BSc in Computer Science
University of Hong Kong