The Case for NL: More Intuitive and Expressive for Complex Constraints

Table of Links

Abstract and 1 Introduction

2 Survey with Industry Professionals

3 RQ1: Real-World use cases that necessitate output constraints

4 RQ2: Benefits of Applying Constraints to LLM Outputs and 4.1 Increasing Prompt-based development Efficiency

4.2 Integrating with Downstream Processes and Workflows

4.3 Satisfying UI and Product Requirements and 4.4 Improving User Experience, Trust, and Adoption

5 How to Articulate output constraints to LLMS and 5.1 The case for GUI: A Quick, Reliable, and Flexible Way of Prototyping Constraints

5.2 The Case for NL: More Intuitive and Expressive for Complex Constraints

6 The Constraint maker Tool and 6.1 Iterative Design and User Feedback

7 Conclusion and References

A. The Survey Instrument

5.2 The Case for NL: More Intuitive and Expressive for Complex Constraints

Respondents found natural language easier for specifying complex constraints than GUIs, especially for extended background contexts or numerous choices that wouldn’t reasonably fit into a GUI. Natural language was also preferred for expressing vague, nuanced, or open-ended constraints, like “don’t include offensive words” or “respond in a cheerful manner.” At a high level, respondents emphasized that natural language provides a more natural, familiar, and expressive way to communicate (potentially multiple) complex constraints, and, “trying to figure out how to use a GUI might be more tedious.”

\ Additionally, some respondents noted that, despite their preference for using GUIs to define constraints from time to time, they ultimately have to use natural language prompts due to API limitations. Moreover, some wished to reference “external resources” in constraints that are not feasible to directly include in prompts (e.g., “a large database / vocabulary”). These suggest that a dedicated “output-constraints” API field for specifying constraints could be advantageous, potentially through the use of a formal language or notation.

\

:::info This paper is available on arxiv under CC BY-NC-SA 4.0 DEED license.

:::

:::info Authors:

(1) Michael Xieyang Liu, Google Research, Pittsburgh, PA, USA ([email protected]);

(2) Frederick Liu, Google Research, Seattle, Washington, USA ([email protected]);

(3) Alexander J. Fiannaca, Google Research, Seattle, Washington, USA ([email protected]);

(4) Terry Koo, Google, Indiana, USA ([email protected]);

(5) Lucas Dixon, Google Research, Paris, France ([email protected]);

(6) Michael Terry, Google Research, Cambridge, Massachusetts, USA ([email protected]);

(7) Carrie J. Cai, Google Research, Mountain View, California, USA ([email protected]).

:::

\