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

19 Mar 2025

Respondents found natural language easier for specifying complex constraints than GUIs

How to Articulate Output Constraints to LLMS

19 Mar 2025

An overarching observation is that respondents preferred using GUI to specify low-level constraints and natural language to express high-level constraints.

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

19 Mar 2025

Satisfying UI and Product Requirements Respondents stressed that it is essential to constrain LLM output to meet UI and product specifications

How We Integrated Downstream Processes and Workflows

19 Mar 2025

This suggests that it could be more advantageous for models to accept output constraints independent of the prompt

The Benefits of Applying Constraints to LLM Outputs

19 Mar 2025

Beyond the aforementioned use cases, our survey respondents reported a range of benefits that the ability of constraining LLM output could offer.

Real-World Use Cases That Necessitate Output Constraints

19 Mar 2025

Below, we discuss a number of interesting insights that emerged from our analysis of the use cases

How We Deployed an Online Survey to Users of an Internal Prompt-Based Prototyping Platform

19 Mar 2025

To get a broad range of insights from people who have experience with prompting and building LLM-powered applications, we deployed an online survey to users

"We Need Structured Output": Towards User-Centered Constraints on Large Language Model Output

19 Mar 2025

We conclude with a discussion on user preferences and needs towards articulating intended constraints for LLMs