CogErgLLM: Exploring Large Language Model Systems Design Perspective Using Cognitive Ergonomics

TL;DR

CogErgLLM addresses the problem that current LLMs often neglect cognitive ergonomics, leading to safety risks, biases, and suboptimal user experiences. It proposes a design framework grounded in cognitive ergonomics, with a methodology to develop and evaluate prototypes. The paper provides practical guidelines, case studies across domains, and ethical considerations. The anticipated impact is safer, more reliable, and ethically sound human-AI interactions across healthcare, education, law, and industry.

Abstract

Integrating cognitive ergonomics with LLMs is crucial for improving safety, reliability, and user satisfaction in human-AI interactions. Current LLM designs often lack this integration, resulting in systems that may not fully align with human cognitive capabilities and limitations. This oversight exacerbates biases in LLM outputs and leads to suboptimal user experiences due to inconsistent application of user-centered design principles. Researchers are increasingly leveraging NLP, particularly LLMs, to model and understand human behavior across social sciences, psychology, psychiatry, health, and neuroscience. Our position paper explores the need to integrate cognitive ergonomics into LLM design, providing a comprehensive framework and practical guidelines for ethical development. By addressing these challenges, we aim to advance safer, more reliable, and ethically sound human-AI interactions.

Figures (3)

• Figure 1: Integration of Cognitive ergonomics and Large Language Models
• Figure 2: Conceptual Foundations for Cognitive Ergonomics in Large Language Models
• Figure 3: Components of CogErgLLM