Examining and Addressing Barriers to Diversity in LLM-Generated Ideas

2026-02-23

AI Summary

This study addresses the limited creative diversity in outputs generated by large language models (LLMs), which may contribute to societal homogenization of innovation. Drawing on cognitive psychology, the work identifies cognitive fixation and knowledge convergence as key underlying mechanisms. To counteract these effects, the authors propose a synergistic prompting intervention that integrates Chain-of-Thought reasoning with semantic anchoring to personas representing ordinary individuals, thereby guiding the model to sample more broadly across diverse knowledge spaces. Experimental results demonstrate that this approach significantly enhances the creative diversity of LLM-generated content, with the combined strategy yielding the strongest effect—marking the first instance in which an LLM surpasses human-level performance in independent creative diversity generation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Ideas generated by independent samples of humans tend to be more diverse than ideas generated from independent LLM samples, raising concerns that widespread reliance on LLMs could homogenize ideation and undermine innovation at a societal level. Drawing on cognitive psychology, we identify (both theoretically and empirically) two mechanisms undermining LLM idea diversity. First, at the individual level, LLMs exhibit fixation just as humans do, where early outputs constrain subsequent ideation. Second, at the collective level, LLMs aggregate knowledge into a unified distribution rather than exhibiting the knowledge partitioning inherent to human populations, where each person occupies a distinct region of the knowledge space. Through four studies, we demonstrate that targeted prompting interventions can address each mechanism independently: Chain-of-Thought (CoT) prompting reduces fixation by encouraging structured reasoning (only in LLMs, not humans), while ordinary personas (versus"creative entrepreneurs"such as Steve Jobs) improve knowledge partitioning by serving as diverse sampling cues, anchoring generation in distinct regions of the semantic space. Combining both approaches produces the highest idea diversity, outperforming humans. These findings offer a theoretically grounded framework for understanding LLM idea diversity and practical strategies for human-AI collaborations that leverage AI's efficiency without compromising the diversity essential to a healthy innovation ecosystem.

Problem

• idea diversity
• large language models
• homogenization
• innovation
• cognitive fixation

Innovation

• idea diversity
• large language models
• cognitive fixation
• knowledge partitioning
• prompting interventions