Argues for modeling LLM interactions as dependent stochastic processes to enable valid sequential uncertainty quantification and change-point monitoring for trustworthiness properties.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sequential statistical inference for Large Language Models: Representation, validity, and monitoring
Argues for modeling LLM interactions as dependent stochastic processes to enable valid sequential uncertainty quantification and change-point monitoring for trustworthiness properties.