Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Beyond Anthropomorphism: a Spectrum of Interface Metaphors for LLMs

Jianna So, Connie Cheng, Sonia Krishna Murthy

TL;DR

A spectrum of metaphors from transparency-driven''anti-anthropomorphism''to uncanny''hyper-anthropomorphism'' is introduced, which shifts interface design away from optimizing usability and toward encouraging critical engagement.

Abstract

Anthropomorphizing conversational technology is a natural human tendency. Today, the anthropomorphic metaphor is overly reinforced across intelligent tools. Large Language Models (LLMs) are particularly anthropomorphized through interface design. While metaphors are inherently partial, anthropomorphic interfaces highlight similarities between LLMs and humans, but mask crucial differences. As a result, the metaphor is often taken literally; users treat LLMs as if they are truly human. With few safeguards in place, this extreme anthropomorphism drives users to delusion and harm. Users also experience dissonance between the ethics of using LLMs, their growing ubiquity, and limited interface alternatives. We propose repositioning anthropomorphism as a design variable, developing opposing extremes as a theoretical framework for how interface metaphors shape and can disrupt the default metaphor. We introduce a spectrum of metaphors from transparency-driven ''anti-anthropomorphism'' to uncanny ''hyper-anthropomorphism''. These metaphors introduce materiality to interface metaphors, exposing LLMs as sociotechnical systems shaped by human labor, infrastructure, and data. This spectrum shifts interface design away from optimizing usability and toward encouraging critical engagement.

Beyond Anthropomorphism: a Spectrum of Interface Metaphors for LLMs

TL;DR

A spectrum of metaphors from transparency-driven''anti-anthropomorphism''to uncanny''hyper-anthropomorphism'' is introduced, which shifts interface design away from optimizing usability and toward encouraging critical engagement.

Abstract

Anthropomorphizing conversational technology is a natural human tendency. Today, the anthropomorphic metaphor is overly reinforced across intelligent tools. Large Language Models (LLMs) are particularly anthropomorphized through interface design. While metaphors are inherently partial, anthropomorphic interfaces highlight similarities between LLMs and humans, but mask crucial differences. As a result, the metaphor is often taken literally; users treat LLMs as if they are truly human. With few safeguards in place, this extreme anthropomorphism drives users to delusion and harm. Users also experience dissonance between the ethics of using LLMs, their growing ubiquity, and limited interface alternatives. We propose repositioning anthropomorphism as a design variable, developing opposing extremes as a theoretical framework for how interface metaphors shape and can disrupt the default metaphor. We introduce a spectrum of metaphors from transparency-driven ''anti-anthropomorphism'' to uncanny ''hyper-anthropomorphism''. These metaphors introduce materiality to interface metaphors, exposing LLMs as sociotechnical systems shaped by human labor, infrastructure, and data. This spectrum shifts interface design away from optimizing usability and toward encouraging critical engagement.
Paper Structure (13 sections, 2 figures)

This paper contains 13 sections, 2 figures.

Table of Contents

  1. Introduction
  2. The anthropomorphic metaphor
  3. The anthropomorphic interface
  4. What is a useful metaphor for LLMs?
  5. A language for mediating mismatched conceptual systems
  6. Support for understanding constituent functions
  7. Highlighting differences, in addition to similarities
  8. Promoting user agency
  9. Levels of intervention in the interface
  10. Metaphors of materiality: from "anti-" to "hyper-" anthropomorphism
  11. Anti-anthropomorphism
  12. Hyper-anthropomorphism
  13. Future work

Figures (2)

  • Figure 1: The interfaces of Claude and ChatGPT when greeting a user in January 2026. In Claude, a disclaimer that the LLM is AI and can make mistakes is shown below the text box, in the smallest font of the interface.
  • Figure 2: Animations designed to build user understanding of LLM processes during natural loading pause. (A-B) demonstrate in context: animations play while the model generates a response, then give way to the completed answer. (C-E) show additional concepts, designed to make a distinct aspects of model behavior visible.