Maxim S. Panov

Embedded Ensembles: Infinite Width Limit and Operating Regimes

2022 · arXiv (Cornell University)

A memory efficient approach to ensembling neural networks is to share most weights among the ensembled models by means of a single reference network. We refer to this strategy as Embedded Ensembling (EE); its particular …

Conformal Prediction for Federated Uncertainty Quantification Under Label Shift

2023 · arXiv (Cornell University)

Federated Learning (FL) is a machine learning framework where many clients collaboratively train models while keeping the training data decentralized. Despite recent advances in FL, the uncertainty quantification topic (UQ) remains partially addressed. Among UQ …

LM-Polygraph: Uncertainty Estimation for Language Models

2023 · arXiv (Cornell University)

Recent advancements in the capabilities of large language models (LLMs) have paved the way for a myriad of groundbreaking applications in various fields. However, a significant challenge arises as these models often "hallucinate", i.e., fabricate …

Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification

2024 · arXiv (Cornell University)

Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccuracies in the generated text might be obscured by the rest of …