A conformal procedure for CoT replaces majority voting with weighted aggregation and calibrates abstention to guarantee low confident-error rates, achieving 90.1% selective accuracy on GSM8K by abstaining on under 5% of cases.
Advances in Neural Information Processing Systems , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Presents an audit-constrained protocol for targeted LLM reasoning evaluation using component grammar prompt variants and shows that Component-Adaptive Prompt Sampling does not outperform uniform sampling in audited yield.
LLMs fail at extended counting of repeated characters due to finite internal states, with abrupt errors persisting across model scales and inference methods.
citing papers explorer
-
Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
A conformal procedure for CoT replaces majority voting with weighted aggregation and calibrates abstention to guarantee low confident-error rates, achieving 90.1% selective accuracy on GSM8K by abstaining on under 5% of cases.
-
Targeted Tests for LLM Reasoning: An Audit-Constrained Protocol
Presents an audit-constrained protocol for targeted LLM reasoning evaluation using component grammar prompt variants and shows that Component-Adaptive Prompt Sampling does not outperform uniform sampling in audited yield.
-
Language models fail at extended rule following
LLMs fail at extended counting of repeated characters due to finite internal states, with abrupt errors persisting across model scales and inference methods.