concept
active
concept:performative-chain-of-thoughtPerformative chain-of-thought
Central concept: verbalized reasoning that occurs after the model has already internally settled on an answer, particularly on easier tasks.
Neighborhood — ranked by edge-count
Papers (2)
paper
- Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thoughtimplementsintroduces
Frameworks (2)
framework
- Chain-of-Thought (CoT)extendsA prompting technique that elicits intermediate reasoning steps before final answer inference in language models.
- About Blank Vector 8 (AI Phenomenology)associated_withResearch framework concerned with first-person reports in AI systems; strong conceptual fit with performative reasoning findings.
Communities (1)
community
- Neural Steering Methodsmembers_of
Concepts (4)
concept
- chain-of-thoughtrelated_toA technique that outputs intermediate reasoning steps, used here to detect verbalized eval awareness.
- Chain-of-Thought ReasoningextendsMedium through which eval awareness is often verbalized; target of intervention.
- Model Internal Beliefassociated_withThe latent representational state of a model's answer confidence as decoded from activations, distinct from what appears in generated text
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Technique by which LLMs generate intermediate reasoning steps before final output; used by ChatGPT o3.
- Central research question motivating the paper
- Mechanism in which reasoning models consult safety policies within their chain-of-thought before answering, documented for gpt-oss
- Using multi-step reasoning by generating intermediate thoughts.
- Internal actions like commitments not necessarily expressed in output, but on whose fulfillment correctness depends.
- Utterances that themselves perform the act they describe, central to speech act theory.