Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.07362 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929310649024512 |
|---|---|
| author | Liu, Michael Xieyang Liu, Frederick Fiannaca, Alexander J. Koo, Terry Dixon, Lucas Terry, Michael Cai, Carrie J. |
| author_facet | Liu, Michael Xieyang Liu, Frederick Fiannaca, Alexander J. Koo, Terry Dixon, Lucas Terry, Michael Cai, Carrie J. |
| contents | Large language models can produce creative and diverse responses. However, to integrate them into current developer workflows, it is essential to constrain their outputs to follow specific formats or standards. In this work, we surveyed 51 experienced industry professionals to understand the range of scenarios and motivations driving the need for output constraints from a user-centered perspective. We identified 134 concrete use cases for constraints at two levels: low-level, which ensures the output adhere to a structured format and an appropriate length, and high-level, which requires the output to follow semantic and stylistic guidelines without hallucination. Critically, applying output constraints could not only streamline the currently repetitive process of developing, testing, and integrating LLM prompts for developers, but also enhance the user experience of LLM-powered features and applications. We conclude with a discussion on user preferences and needs towards articulating intended constraints for LLMs, alongside an initial design for a constraint prototyping tool. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07362 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | "We Need Structured Output": Towards User-centered Constraints on Large Language Model Output Liu, Michael Xieyang Liu, Frederick Fiannaca, Alexander J. Koo, Terry Dixon, Lucas Terry, Michael Cai, Carrie J. Human-Computer Interaction Large language models can produce creative and diverse responses. However, to integrate them into current developer workflows, it is essential to constrain their outputs to follow specific formats or standards. In this work, we surveyed 51 experienced industry professionals to understand the range of scenarios and motivations driving the need for output constraints from a user-centered perspective. We identified 134 concrete use cases for constraints at two levels: low-level, which ensures the output adhere to a structured format and an appropriate length, and high-level, which requires the output to follow semantic and stylistic guidelines without hallucination. Critically, applying output constraints could not only streamline the currently repetitive process of developing, testing, and integrating LLM prompts for developers, but also enhance the user experience of LLM-powered features and applications. We conclude with a discussion on user preferences and needs towards articulating intended constraints for LLMs, alongside an initial design for a constraint prototyping tool. |
| title | "We Need Structured Output": Towards User-centered Constraints on Large Language Model Output |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2404.07362 |