Internal per-step geometry predicts when a reasoning chain has gone wrong better than output confidence does — a usable signal for deciding when to re-run, branch, or escalate a reasoning trace.
Terms in this piece · Glossary
chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.
alignment — The work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
articleControlling Reasoning Effort in LLMsSebastian Raschka, PhD
articleWhen Chain-of-Thought Helps and When It Hurts: An Empirical Investigation of the Serial-Depth Bottleneck in LLM ReasoningTughanbulut Kurtulush
articleAre the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon StatementsXinke Tong, Xuanming Zhang, Tianyi Tang, An Yang, Jiatu Hu, Guojie Lin, Zhenzhen Shi, Lingfeng Zeng, Boyu Yang, Bing Zhao, Hu Wei, Lin Qu, Dayiheng Liu