Tim Baldwin — accepted AI-conference papers

2026

Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation

Sayantan Dasgupta, Trevor Cohn, Tim Baldwin

ICML 2026poster

The core learning signal used in language model distillation is the standard Kullback-Leibler (KL) divergence between the distribution of the student and the teacher. Traditional KL divergence tends to be dominated by the teacher’s highest-probability modes, thus diminishing the influence of less pr…

Cited by 0 Source ↗Scholar ↗

2026

Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads

Artem Vazhentsev, Lyudmila Rvanova, Gleb Kuzmin, Ekaterina Fadeeva, Ivan Lazichny, Alexander Panchenko +5

ICML 2026poster

Recent progress in large language models (LLMs) has led to systems capable of producing text with remarkable fluency. However, these models are still prone to factual inaccuracies, often referred to as \``hallucinations''. One strategy to alleviate this issue is uncertainty quantification (UQ), but …

Cited by 0 Source ↗Scholar ↗