Publication
UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models
Jan 1, 2025 · Open MIND
OpenAlex citations: 1Open
Public profile
Maiya Goloburda
Connected with DSML. This person's Telegram account has been confirmed through DSML Kazakhstan.@maiyagoloburda
I am a Data Scientist with focus on NLP. My research interests are uncertainty quantification and safety for LLMs. In my free time, I enjoy running, reading, and paint-by-numbers.
Astana, KazakhstanMBZUAI 2024-2026, NU 2020-2024
Featured
A few things that best show this member's work and contribution.
How I can help
I am always open to chat about studying at NU/MBZUAI, interesting NLP research.
Looking to connect
Connect with like-minded people, exchange ideas, and discuss research 🐈 🐈 🐈 🐈 🐈 🐈
Research and publications
A compact preview of this member's public research layer.
My primary area of interest is Uncertainty Quantification for LLMs. In very simple terms, I am trying to understand how we can determine when a model knows - and doesn't know - what it is talking about. I also have some interest in LLM safety and trustworthiness, but more so as a casual learner than a practitioner.
NLPUncertianty QuantificationLLM SafetyTrustworthy ML