Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models
In-context learning is commonly interpreted as a form of conditional inference, in which the prompt specifies a context and the model's output is treated as an estimate of the corresponding conditional distribution. If this interpretation holds, then LLM estimates should satisfy basic probabilistic identities. In particular, the law of total probability asserts that prior-weighted conditional distributions aggregate into population-level marginals over any valid partition of the population. In this work, we investigate to what extent LLM estimates adhere to this self-consistency principle. We
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%NirDiamant/Prompt_Engineering →
“Fuzzy title match (0.73): “Partition, Prompt, Aggregate: Statistical Self-Consistency i” ≈ “NirDiamant/Prompt_Engineering””
- FuzzySimilar title/name (fuzzy) · 59%linshenkx/prompt-optimizer →
“Fuzzy title match (0.73): “Partition, Prompt, Aggregate: Statistical Self-Consistency i” ≈ “linshenkx/prompt-optimizer””
- LinkedLinked via arxiv author · 85%Patrik Wolf →
“Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models”
- LinkedLinked via arxiv author · 85%Thomas Kleine Buening →
“Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models”
- LinkedLinked via arxiv author · 85%Andreas Krause →
“Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models”
- LinkedLinked via arxiv author · 85%Celestine Mendler-Dünner →
“Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models”