Attention structures in Large Language Models (LLMs) boost Bayesian Model Averaging (BMA) implementation, and with sufficient examples in the prompt, attention performs BMA under the Gaussian linear In-Context Learning (ICL) model.

Authors

• Person: Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche Organization: AISTATS
  Track: Poster Session 3 - aistats 2026

Sources

• Track: Poster Session 3 - aistats 2026 virtual.aistats.org Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche · AISTATS via serper

Referenced by nodes (2)

• Large Language Models concept
• In-Context Learning concept