2 papers
stat.ML2026
LLMs are Bayesian, In Expectation, Not in Realization
Leon Chlon, Fatima Sheaib, Zein Khamis +3
Bayesian accounts of in-context learning face a direct objection: exact posterior predictives for exchangeable data are invariant to task-preserving order, yet transformers change…
stat.ML2026
Attention Deficits in Language Models: Causal Explanations for Procedural Hallucinations
Ahmed Karim, Fatima Sheaib, Zein Khamis +3
Large language models can follow complex procedures yet fail at a seemingly trivial final step: reporting a value they themselves computed moments earlier. We study this phenomenon…