Addressing Social Misattributions of Large Language Models: An HCXAI-based Approach

TL;DR

This paper extends the Social Transparency framework within human-centered explainable AI to mitigate social misattributions of large language models, especially in sensitive contexts like mental health, promoting ethical and responsible AI use.

Contribution

It introduces a fifth 'W-question' to the Social Transparency framework to clarify social attributions of LLMs, reducing misperceptions and ethical risks.

Findings

Enhanced framework clarifies social attributions of LLMs.

Reduces risks of emotional manipulation and epistemic injustice.

Promotes ethically responsible AI deployment.

Abstract

Human-centered explainable AI (HCXAI) advocates for the integration of social aspects into AI explanations. Central to the HCXAI discourse is the Social Transparency (ST) framework, which aims to make the socio-organizational context of AI systems accessible to their users. In this work, we suggest extending the ST framework to address the risks of social misattributions in Large Language Models (LLMs), particularly in sensitive areas like mental health. In fact LLMs, which are remarkably capable of simulating roles and personas, may lead to mismatches between designers' intentions and users' perceptions of social attributes, risking to promote emotional manipulation and dangerous behaviors, cases of epistemic injustice, and unwarranted trust. To address these issues, we propose enhancing the ST framework with a fifth 'W-question' to clarify the specific social attributions assigned to LLMs by its designers and users. This addition aims to bridge the gap between LLM capabilities and user perceptions, promoting the ethically responsible development and use of LLM-based technology.