GenLine and GenForm: Two Tools for Interacting with Generative Language Models in a Code Editor

By Ellen Jiang, Edwin Toh, A. Molina, Aaron Donsbach, Carrie J. Cai, Michael Terry. 2021

27 citations recorded by the source corpus.

A large, generative language model’s output can be influenced through well-designed prompts, or text-based inputs that establish textual patterns that the model replicates in its output [6]. These capabilities create new opportunities for novel interactions with large, generative language models. We present a macro system with two tools that allow users to invoke language model prompts as macros in a code editor. GenLine allows users to execute macros inline as they write code in the editor (e.g., “Make an OK button” produces the equivalent HTML). GenForm provides a form-like interface where the user provides input that is then transformed into multiple pieces of output at the same time (e.g., a description of web code is transformed into HTML, CSS, and JavaScript).

Subfields: Artificial Intelligence, Information Systems, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tongshuang Sherry Wu
2. Percy Liang
3. Carrie J. Cai
4. Michael S. Bernstein
5. Michael Terry
6. Richmond Y. Wong
7. Qian Yang
8. J.D. Zamfirescu-Pereira

In Information Systems

1. Percy Liang
2. Carrie J. Cai
3. Qian Yang
4. J.D. Zamfirescu-Pereira
5. Michael Terry
6. Meredith Ringel Morris
7. Michael S. Bernstein
8. Bjoern Hartmann

In Code Generation & Program Synthesis

1. Percy Liang
2. Michael S. Bernstein

Citations in the corpus

• AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts (2021, background): “Finally, the closest work to ours might be online interfaces for users to interactively create prompts1, or interfaces enabling users to perform natural language programming of code using a large language model [34].”
• Social Simulacra: Creating Populated Prototypes for Social Computing Systems (2022, background): “Furthermore, prompt design can better elicit the desired model behavior [36, 37, 49].”
• Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts (2023, background): “This excitement around LLMs and prompting is propelling a rapidly growing set of LLM-powered applications [23] and prompt design tools [3, 20, 32].”