CoT

Creator

Creator

Seonglae Cho

Created

Created

2023 Mar 21 13:54

Editor

Editor

Seonglae Cho

Edited

Edited

2026 May 14 17:45

Refs

Refs

Reasoning Model

Reasoning Interpretability

Chain-of-Thought

The impact of reasoning process prompts on results

An important finding is that the effectiveness of CoT increases as the language model size grows

CoT Variants

Chain of Hindsight

LogiCoT

notion image

notion image

CoT Group - Global CoT

Figure 6: Embedding of a semantic clustering graph made with 100 rollouts on the “tricky sisters” prompt via gpt-oss-20b. Each rollout is depicted in a different color. — Figure 6: Embedding of a semantic clustering graph made with 100 rollouts on the “tricky sisters” prompt via gpt-oss-20b. Each rollout is depicted in a different color.

Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought — LessWrong

Authors: Riya Tyagi, Daria Ivanova, Arthur Conmy, Neel Nanda …

Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought — LessWrong

https://www.lesswrong.com/posts/q9g9zuudd3Pvw2cbj/global-cot-analysis-initial-attempts-to-uncover-patterns-1

Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought — LessWrong

https://arxiv.org/pdf/2201.11903

Maximizing the Potential of LLMs: A Guide to Prompt Engineering

Maximizing the Potential of LLMs: A Guide to Prompt Engineering

https://www.ruxu.dev/articles/ai/maximizing-the-potential-of-llms

Backlinks

Interpretable AI OmniJARVIS AI Scaling AI Jailbreak SAE Implementation Philosophy LLM Judge Model Reasoning Model Big-Bench AI Scientist Preparedness Framework COCONUT

Recommendations

//////////