AI News HubLIVE
Original source3 min read

Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement

Large language models often give inconsistent answers to the same decision problem across runs. This study introduces the Cognitive Kernel Model (CKM), a prompt-level state enforcement layer that forces models to separate input into fact, heuristic, and emotion categories before deciding. Experiments on 26 LLMs with 37,403 observations show CKM significantly reduces output variability (Hedges' g=1.09) and decision-flip rates by up to 82%, with effects growing under sampling stochasticity. However, CKM does not improve reasoning correctness.

SourcearXiv Computational LinguisticsAuthor: Gi-Hun Lee, Joong Yull Park

-->

[Submitted on 5 Jun 2026]

Title:Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement

View a PDF of the paper titled Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement, by Gi-Hun Lee and 1 other authors

View PDF HTML (experimental)

Abstract:Large language models (LLMs) can give different answers to the same decision problem across runs, and reverse a decision when their own prior answer returns as context. We ask whether this instability can be measured and partially reduced without changing model weights.

We test the Cognitive Kernel Model (CKM), a prompt-level state-enforcement layer. Before deciding, the model must separate its input into three epistemic roles: Fact (given or verifiable), Heuristic (inferred or assumed), and Emotion (evaluative or priority signal). CKM adds no capability; it forces the model to track what kind of information it uses before acting. Formally it maintains a structured state S_t = {F_t, H_t, E_t} updated by a transition function.

We evaluate CKM on Korean-language decision scenarios (ambiguity, ethical conflict, resource allocation, error handling) across 26 LLMs from four vendors and 37,403 observations, via four core experiments, a 4-arm ablation, a 5-arm sham-restriction ablation, and a temperature probe. Findings:

(1) CKM reduces repeated-output variability (random-effects Hedges' g=1.09, 95% CI [0.83, 1.35], 31 model pairs);

(2) state persistence cuts the decision-flip rate by 82% in newer models (g=1.52);

(3) the effect is not JSON formatting alone (value-only recomputation, g=2.24);

(4) intrinsic randomness under fixed anchor states is negligible;

(5) the advantage grows under sampling stochasticity (g=2.87 at temperature 0.7);

(6) a sham ablation attributes about 45% of the gain to structural scaffolding and 55% to Fact/Heuristic/Emotion content, and CKM is the only arm that both raises consistency and reduces flipping.

CKM does not improve reasoning correctness. The narrower result: behavioral consistency is measurable, varies across models, and is partially improvable by forcing models to separate facts, assumptions, and evaluative signals before deciding.

Comments: 40 pages, 6 figures; 54-page supplementary material included as an ancillary file. Code, prompts, and data: this https URL

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)

ACM classes: I.2.7; I.2.0

Cite as: arXiv:2607.24765 [cs.CL]

(or arXiv:2607.24765v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.24765

arXiv-issued DOI via DataCite

Submission history

From: Gihun Lee Dr [view email] [v1] Fri, 5 Jun 2026 12:36:36 UTC (483 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement, by Gi-Hun Lee and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Ancillary-file links:

Ancillary files (details):

supplementary.pdf

Current browse context:

cs.CL

new | recent | 2026-07

Change to browse by:

cs cs.AI cs.HC

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)