3 papers
cs.CL2026
Committed Before Reasoning: Behavioral Reproduction and Preliminary Activation-Level Evidence of Answer Pre-Commitment in an Open-Weight LLM
Heejin Jo
Chat models sometimes commit to an answer and then produce reasoning that justifies it rather than deriving it -- even when the answer contradicts a task premise. We study a minima…
cs.AI2026
Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem
Heejin Jo
Large language models consistently fail the "car wash problem," a viral reasoning benchmark requiring implicit physical constraint inference. We present a variable isolation study…
cs.AI2026
Prompt Complexity Dilutes Structured Reasoning: A Follow-Up Study on the Car Wash Problem
Heejin Jo
In a previous study [Jo, 2026], STAR reasoning (Situation, Task, Action, Result) raised car wash problem accuracy from 0% to 85% on Claude Sonnet 4.5, and to 100% with additional p…