Cognitive Prompts Using Guilford's Structure of Intellect Model

2025-03-27

AI Summary

Large language models (LLMs) exhibit instability in structured reasoning, resulting in weak logical consistency and poor cross-task adaptability. Method: Grounded in Guilford’s Structure of Intellect (SOI) theory, this work introduces— for the first time— a systematic, theory-driven cognitive prompting framework into prompt engineering. The framework explicitly guides LLMs through core cognitive operations—including pattern recognition, memory retrieval, and evaluation—via interpretable, modular prompts and structured reasoning chains. It integrates cognitive prompting, SOI-informed modeling, and chain-of-reasoning design to shift from heuristic prompting toward principled, theory-grounded reasoning guidance. Contribution/Results: Experiments demonstrate significant improvements in multi-step reasoning, cross-domain generalization, and logical consistency across diverse benchmarks. The results validate that psychologically grounded theories can effectively enhance controllability, reliability, and scalability of LLM reasoning.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Large language models (LLMs) demonstrate strong language generation capabilities but often struggle with structured reasoning, leading to inconsistent or suboptimal problem-solving. To mitigate this limitation, Guilford's Structure of Intellect (SOI) model - a foundational framework from intelligence theory - is leveraged as the basis for cognitive prompt engineering. The SOI model categorizes cognitive operations such as pattern recognition, memory retrieval, and evaluation, offering a systematic approach to enhancing LLM reasoning and decision-making. This position paper presents a novel cognitive prompting approach for enforcing SOI-inspired reasoning for improving clarity, coherence, and adaptability in model responses.

Problem

• Enhancing structured reasoning in large language models
• Applying Guilford's SOI model to improve LLM responses
• Addressing inconsistent problem-solving with cognitive prompts

Innovation

• Leveraging Guilford's SOI model for cognitive prompts
• Enhancing LLM reasoning with structured cognitive operations
• Improving response clarity via SOI-inspired prompting