3

Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
We propose semantic entropy probes (SEPs), a cheap and reliable method for uncertainty quantification in Large Language Models (LLMs). …
Jannik Kossen, Jiatong Han, Muhammed Razzak, Lisa Schut, Shreshth A Malik*, Yarin Gal
Preprint Cite
High-Cadence Thermospheric Density Estimation enabled by Machine Learning on Solar Imagery
Accurate estimation of thermospheric density is critical for precise modeling of satellite drag forces in low Earth orbit (LEO). …
Shreshth A Malik*, James Walsh*, Giacomo Acciarini, Thomas E. Berger, Atilim Gunes Baydin
Preprint Cite
BatchGFN: Generative Flow Networks for Batch Active Learning
We introduce BatchGFN—a novel approach for pool-based active learning that uses generative flow networks to sample sets of data …
Shreshth A Malik*, Salem Lahlou, Andrew Jesson, Moksh Jain, Nikolay Malkin, Tristan Deleu, Yoshua Bengio, Yarin Gal
Preprint Cite Code
Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels
Automated planetary transit detection has become vital to prioritize candidates for expert analysis given the scale of modern …
Shreshth A Malik*, Nora L Eisner, Chris J Lintott, Yarin Gal
Preprint Cite Code
Multi-Modal Fusion by Meta-Initialization
When experience is scarce, models may have insufficient information to adapt to a new task. In this case, auxiliary information - such …
Matthew T Jackson*, Shreshth A Malik*, Michael T Matthews, Yousuf Mohamed-Ahmed
Preprint Cite Code DOI