Cognitive Prompts Using Guilford's Structure of Intellect Model

TL;DR

The paper addresses the challenge that LLMs struggle with structured reasoning and proposes a cognitive prompting approach based on Guilford’s Structure of Intellect (SOI) to enforce explicit cognitive strategies during problem solving. It operationalizes SOI by organizing prompts around three dimensions—operations, contents, and products—allowing the model to select reasoning modes, information types, and output structures. The authors illustrate the method with a Step-by-Step SOI Analysis example and situate it among related prompting and optimization techniques (CoT, cognitive prompting, ReAct, Prompt Breeder, APE, OPRO). The work aims to improve interpretability, coherence, and adaptability of LLM reasoning and suggests extensions to reinforcement learning and multimodal reasoning.

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.