More capable LLMs produce worse distributional forecasts on superlinear growth time series with tail risks of regime change, with the error concentrated in the upper tail; this reverses on conventional threshold metrics.
International Conference on Machine Learning (ICML) , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Derives a closed-form impossibility bound and feasibility test for conformal risk control on structured LLM outputs, with empirical comparison of bounds and adaptive inference across models and tasks.
citing papers explorer
-
Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most
More capable LLMs produce worse distributional forecasts on superlinear growth time series with tail risks of regime change, with the error concentrated in the upper tail; this reverses on conventional threshold metrics.
-
When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generation
Derives a closed-form impossibility bound and feasibility test for conformal risk control on structured LLM outputs, with empirical comparison of bounds and adaptive inference across models and tasks.