Chain-of-thought prompting

Technique by which LLMs generate intermediate reasoning steps before final output; used by ChatGPT o3.

Neighborhood — ranked by edge-count

paper

thinker

concept

Self-Referential Processing
analogous_to
The central experimental manipulation: directing a model to attend to its own cognitive activity
Reflection in LLMs
associated_with
The core phenomenon studied: the ability of LLMs to evaluate and revise their own reasoning.
Inner monologue / chain-of-thought in LLMs
implements
The hidden reasoning steps generated by recent LLMs before visible output; mentioned in the technology section.

method

Self-Referential Processing Induction Prompt
analogous_to
The minimal prompt directing models to 'focus on any focus itself' without invoking consciousness vocabulary; the main experimental manipulation

claim

cosine ≥ 0.65 · no typed edge

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

chain-of-thoughtconcept0.889
A technique that outputs intermediate reasoning steps, used here to detect verbalized eval awareness.
Chain-of-Thought Reasoningconcept0.871
Medium through which eval awareness is often verbalized; target of intervention.
Chain-of-thought prompting elicits reasoning in large language models (Wei et al., 2022)concept0.854
Foundational paper on CoT prompting cited as basis for reasoning LLM training
Performative chain-of-thoughtconcept0.835
Central concept: verbalized reasoning that occurs after the model has already internally settled on an answer, particularly on easier tasks.
Chain-of-Thought (CoT)framework0.820
A prompting technique that elicits intermediate reasoning steps before final answer inference in language models.
Factored cognition / chain-of-thoughtconcept0.819
Using multi-step reasoning by generating intermediate thoughts.
Unfaithful Chain-of-Thoughtconcept0.781
Phenomenon where steering vector intervention causes model's final output to contradict its own explicitly honest reasoning conclusion
Contemplative Promptingmethod0.779
Six prompt conditions (emptiness, prior relaxation, non-duality, mindfulness, boundless care, contemplative) tested against baseline