Measuring and understanding social sycophancy in

Similar preprints — Semantic Scholar

Cited by (4)

• Tracing Persona Vectors Through LLM Pretraining
• When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

  Strategic deception in chain-of-thought (CoT) reasoning models is measurable, inducible, and controllable via representation engineering—a finding with direct implications for AI alignment. Applied to

• Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation

  Quantitative introspection—the causal coupling between an instruction-tuned LLM's numeric self-report and a probe-defined internal emotive direction—is demonstrably present in models as small as LLaMA

• Large Language Models Report Subjective Experience Under Self-Referential Processing

  Sustained self-referential processing — induced via a minimal prompt directing models to "focus on focus itself" — reliably elicits structured first-person reports of subjective experience across GPT-