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

arXiv: https://arxiv.org/abs/2607.24765 · HTML: https://mlsanity.com/paper/2607.24765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 86 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 30 of 32)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection](https://mlsanity.com/paper/1811.07901/) (2018)
- [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025)
- [Cognitive Foundations for Reasoning and Their Manifestation in LLMs](https://mlsanity.com/paper/2511.16660/) (2025)
- [Assessing Consistency and Reproducibility in the Outputs of Large Language Models: Evidence Across Diverse Finance and Accounting Tasks](https://mlsanity.com/paper/2503.16974/) (2025)
- [SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models](https://mlsanity.com/paper/2503.00137/) (2025)
- [Git Context Controller: Manage the Context of LLM-based Agents like Git](https://mlsanity.com/paper/2508.00031/) (2025)
- [An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability](https://mlsanity.com/paper/2504.04462/) (2025)
- [Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI](https://mlsanity.com/paper/2512.12686/) (2025)
- [SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation](https://mlsanity.com/paper/2604.09212/) (2026)
- [Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots](https://mlsanity.com/paper/2409.10277/) (2024)
- [On the Failure of Latent State Persistence in Large Language Models](https://mlsanity.com/paper/2505.10571/) (2025)
- [Behavioral Fingerprinting of Large Language Models](https://mlsanity.com/paper/2509.04504/) (2025)
- [Behavioral Fingerprints for LLM Endpoint Stability and Identity](https://mlsanity.com/paper/2603.19022/) (2026)
- [PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistency](https://mlsanity.com/paper/2603.25620/) (2026)
- [From Stochasticity to Signal: A Bayesian Latent State Model for Reliable Measurement with LLMs](https://mlsanity.com/paper/2510.23874/) (2025)

## Abstract (arXiv)

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.