Token-level confidence trajectories in LLMs encode a content-agnostic geometry that separates correct and incorrect reasoning traces and supports a lightweight correctness estimator called NeuralConf.
Scaling LLM test-time compute optimally can be more effective than scaling parameters for reasoning,
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
-
Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning
Token-level confidence trajectories in LLMs encode a content-agnostic geometry that separates correct and incorrect reasoning traces and supports a lightweight correctness estimator called NeuralConf.