Chain-of-thought prompting elicits reasoning in large language models (Wei et al., 2022)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Chain-of-thought promptingmethod0.854
  Technique by which LLMs generate intermediate reasoning steps before final output; used by ChatGPT o3.
• Chain-of-Thought Reasoningconcept0.850
  Medium through which eval awareness is often verbalized; target of intervention.
• Chain-of-thought reasoning improves large model accuracy on HHH binary comparisons, reaching ~78% for 52B model, competitive with human-feedback PM.finding0.811
  Figure 4 shows CoT improves over zero-shot, and ensembled CoT further boosts accuracy.
• A small number of high-quality human demonstrations of chain-of-thought reasoning could be used to improve and focus performance.hypothesis0.808
  Section 6 mentions high-quality human demos could improve natural language feedback.
• does chain-of-thought text faithfully reveal a model's internal reasoning process, or does it constitute performative theater?question0.799
  Central research question motivating the paper
• Prompting functions as a control interface over learned programs in the model's latent space rather than a fundamental change to architecture, analogous to chain-of-thought eliciting distinct reasoning regimesclaim0.797
  Mechanistic framing of how self-referential prompting achieves its effects without architecture modification
• chain-of-thoughtconcept0.788
  A technique that outputs intermediate reasoning steps, used here to detect verbalized eval awareness.
• Chain-of-thought reasoning improves the transparency and performance of AI decision making in harmlessness evaluation.claim0.786
  CoT improves accuracy on HHH evals and makes the decision process legible.