When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models

arXiv:2609.39846 · cs.CL, cs.AI, cs.HC · Submitted 2026-09-30 · Read on arXiv

cs.CL, cs.AI, cs.HC

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• Accuracy — 40× in this paper · explained in 1 episode
• Benchmark — 21× in this paper · explained in 2 episodes
• Consistency — 13× in this paper · explained in 3 episodes
• Task Accuracy — 11× in this paper
• Reasoning Coherence — 9× in this paper
• Role Voice — 9× in this paper
• Alignment — 8× in this paper · explained in 1 episode
• Capability Consistency — 8× in this paper
• In-Role Accuracy — 8× in this paper
• Above-Role Accuracy — 7× in this paper
• Trace — 5× in this paper · explained in 2 episodes
• Abstention — 4× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Persona Prompting — 2× in this paper · explained in 2 episodes
• Prompt Engineering — 2× in this paper · explained in 4 episodes
• Thinking mode — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Agentic AI — 1× in this paper · explained in 1 episode
• Agentic AI systems — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Frozen model — 1× in this paper · explained in 2 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Gemma 4 Technical Report
• Olmo 3
• gpt-oss-120b & gpt-oss-20b Model Card
• Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering