Gi-Hun Lee, Joong Park
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large language models (LLMs) can give different answers to the same decision problem across repeated runs. They can also change their decisions when their own previous answer is reintroduced as context. This paper asks whether that instability can be measured and partially reduced without changing model weights. We test a lightweight intervention called the Cognitive Kernel Model (CKM). Before making a decision, the model must separate the input into three epistemic roles: Fact (what is given or verifiable), Heuristic (what is inferred or assumed), and Emotion (what carries evaluative or priority signal). In practical terms, CKM is a prompt-level state-enforcement layer. It does not make the model more capable; it forces the model to track what kind of information it is using before it acts. Formally, CKM maintains a structured state 𝑆 𝑡 = {𝐹 𝑡 , 𝐻 𝑡 , 𝐸 𝑡 } and updates it through a state transition function: 𝑆 𝑡+1 = 𝛿(𝑆 𝑡 , Ω 𝑥,𝑡 , Ω Engine 𝑡 ). We evaluated CKM on Korean-language student decision scenarios involving ambiguity resolution, ethical conflict, resource allocation, and error handling. The evaluation includes four core experiments, a 4-arm ablation, a 5-arm sham-restriction ablation, and a temperature robustness probe. The dataset spans 26 unique LLM models from four vendors (OpenAI, Anthropic, Google, xAI), two model generations, and 37,403 total observations (35,475 primary + 1,928 case-study observations). Six findings emerged.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2607.24765")
get_code_for_paper("2607.24765")
have("2607.24765")
Connect an agent — have() is free.