A Fuzzy Logic Prompting Framework for Large Language Models in Adaptive and Uncertain Tasks

TL;DR

This paper presents a fuzzy logic-based prompting framework for large language models that enhances adaptivity, safety, and interpretability in dynamic, user-centered tasks like education and content generation.

Contribution

It introduces a modular, human learning theory grounded prompting architecture that enables LLMs to adapt behavior without fine-tuning or external control.

Findings

Improves scaffolding quality and adaptivity in simulated tutoring tasks

Outperforms standard prompting baselines across multiple models

Shows potential in domains beyond education, such as game content generation

Abstract

We introduce a modular prompting framework that supports safer and more adaptive use of large language models (LLMs) across dynamic, user-centered tasks. Grounded in human learning theory, particularly the Zone of Proximal Development (ZPD), our method combines a natural language boundary prompt with a control schema encoded with fuzzy scaffolding logic and adaptation rules. This architecture enables LLMs to modulate behavior in response to user state without requiring fine-tuning or external orchestration. In a simulated intelligent tutoring setting, the framework improves scaffolding quality, adaptivity, and instructional alignment across multiple models, outperforming standard prompting baselines. Evaluation is conducted using rubric-based LLM graders at scale. While initially developed for education, the framework has shown promise in other interaction-heavy domains, such as procedural content generation for games. Designed for safe deployment, it provides a reusable methodology for structuring interpretable, goal-aligned LLM behavior in uncertain or evolving contexts.