Robust Langevin Sampling under State-Dependent Heavy-Tailed Noise with Applications to LLM Fine-Tuning
Bayesian fine-tuning experiments with LLMs and vision-language models support the proposed state-dependent heavy-tailed oracle model and show that RA-LMC matches or outperforms state-of-the-art baselines in accuracy and uncertainty quantification.
M. Şahin, Ege C. Kaya, Arda Fazla et al.
· 0 citations