Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Applying the Gricean Maxims to a Human-LLM Interaction Cycle: Design Insights from a Participatory Approach

Yoonsu Kim, Brandon Chin, Kihoon Son, Seoyoung Kim, Juho Kim

TL;DR

The paper addresses the challenge that LLM-human interactions often fail to infer contextual nuances and user intent. It proposes applying Gricean Maxims as a design lens and employs participatory design workshops with communication experts, designers, and end-users to derive nine design considerations for the three-stage human-LLM interaction cycle (users communicate goals, LLM interprets and acts, users assess output). The findings include reinterpretations of maxims for HAI and a concrete mapping of design considerations (DC1–DC9) to actionable features such as task decomposition, hierarchical output, explainability, and memory management. Although empirical validation is not yet conducted, the framework offers practical, stakeholder-informed guidance for building more cooperative, user-centered LLM-based systems and outlines clear directions for future evaluation and prototyping.

Abstract

While large language models (LLMs) are increasingly used to assist users in various tasks through natural language interactions, these interactions often fall short due to LLMs' limited ability to infer contextual nuances and user intentions, unlike humans. To address this challenge, we draw inspiration from the Gricean Maxims--human communication theory that suggests principles of effective communication--and aim to derive design insights for enhancing human-AI interactions (HAI). Through participatory design workshops with communication experts, designers, and end-users, we identified ways to apply these maxims across the stages of the HAI cycle. Our findings include reinterpreted maxims tailored to human-LLM contexts and nine actionable design considerations categorized by interaction stage. These insights provide a concrete framework for designing more cooperative and user-centered LLM-based systems, bridging theoretical foundations in communication with practical applications in HAI.

Applying the Gricean Maxims to a Human-LLM Interaction Cycle: Design Insights from a Participatory Approach

TL;DR

The paper addresses the challenge that LLM-human interactions often fail to infer contextual nuances and user intent. It proposes applying Gricean Maxims as a design lens and employs participatory design workshops with communication experts, designers, and end-users to derive nine design considerations for the three-stage human-LLM interaction cycle (users communicate goals, LLM interprets and acts, users assess output). The findings include reinterpretations of maxims for HAI and a concrete mapping of design considerations (DC1–DC9) to actionable features such as task decomposition, hierarchical output, explainability, and memory management. Although empirical validation is not yet conducted, the framework offers practical, stakeholder-informed guidance for building more cooperative, user-centered LLM-based systems and outlines clear directions for future evaluation and prototyping.

Abstract

While large language models (LLMs) are increasingly used to assist users in various tasks through natural language interactions, these interactions often fall short due to LLMs' limited ability to infer contextual nuances and user intentions, unlike humans. To address this challenge, we draw inspiration from the Gricean Maxims--human communication theory that suggests principles of effective communication--and aim to derive design insights for enhancing human-AI interactions (HAI). Through participatory design workshops with communication experts, designers, and end-users, we identified ways to apply these maxims across the stages of the HAI cycle. Our findings include reinterpreted maxims tailored to human-LLM contexts and nine actionable design considerations categorized by interaction stage. These insights provide a concrete framework for designing more cooperative and user-centered LLM-based systems, bridging theoretical foundations in communication with practical applications in HAI.

Paper Structure

This paper contains 17 sections, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Cooperative Principle and Gricean Maxims
  4. Gricean Maxim in Human-AI Interaction
  5. Participatory Design Workshop
  6. Recruitment
  7. Participants
  8. Workshop Protocol
  9. Workshop Analysis
  10. Workshop Findings
  11. Reinterpretation of Gricean Maxims in the context of human-LLM interaction
  12. Design considerations for enhancing human-LLM interaction grounded in Gricean Maxims
  13. Mapping design considerations into a human-AI interaction cycle
  14. Limitation and Future Work
  15. appendix
  16. ...and 2 more sections

Figures (1)

  • Figure 1: An example of a FigJam Board that we used in our participatory design workshop. It includes (1) Introduction of the workshop and its objectives; (2) Tutorial on FigJam, the collaborative tool used for the workshop; (3) Explanation of Gricean Maxims; (4) LLM conversation analysis, which is pre-submitted from the LLM user, identifying areas for improvement based on Gricean Maxims (with conversation content blurred for privacy protection); (5) Brainstorming design Ideas, (6) Example design features, which are provided after deriving a few design ideas from analyzing two turns of conversation; (7) Refining and combining design ideas into actionable solutions.