Generative agents: Interactive simulacra of human behavior

JS Park, J O'Brien, CJ Cai, MR Morris, P Liang… - Proceedings of the 36th …, 2023 - dl.acm.org
Believable proxies of human behavior can empower interactive applications ranging from
immersive environments to rehearsal spaces for interpersonal communication to prototyping …

Programming without a programming language: Challenges and opportunities for designing developer tools for prompt programming

AJ Fiannaca, C Kulkarni, CJ Cai, M Terry - Extended Abstracts of the …, 2023 - dl.acm.org
Existing tools for writing prompts for language models (known as “prompt programming”)
provide little support to prompt programmers. Consequently, as prompts become more …

Promptaid: Prompt exploration, perturbation, testing and iteration using visual analytics for large language models

A Mishra, U Soni, A Arunkumar, J Huang… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) have gained widespread popularity due to their ability to
perform ad-hoc Natural Language Processing (NLP) tasks with a simple natural language …

Automatic prompt optimization with" gradient descent" and beam search

R Pryzant, D Iter, J Li, YT Lee, C Zhu… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) have shown impressive performance as general purpose
agents, but their abilities remain highly dependent on prompts which are hand written with …

Social simulacra: Creating populated prototypes for social computing systems

JS Park, L Popowski, C Cai, MR Morris… - Proceedings of the 35th …, 2022 - dl.acm.org
Social computing prototypes probe the social behaviors that may arise in an envisioned
system design. This prototyping practice is currently limited to recruiting small groups of …

Deid-gpt: Zero-shot medical text de-identification by gpt-4

Z Liu, Y Huang, X Yu, L Zhang, Z Wu, C Cao… - arXiv preprint arXiv …, 2023 - arxiv.org
The digitization of healthcare has facilitated the sharing and re-using of medical data but has
also raised concerns about confidentiality and privacy. HIPAA (Health Insurance Portability …

[HTML][HTML] Screening articles for systematic reviews with ChatGPT

E Syriani, I David, G Kumar - Journal of Computer Languages, 2024 - Elsevier
Systematic reviews (SRs) provide valuable evidence for guiding new research directions.
However, the manual effort involved in selecting articles for inclusion in an SR is error-prone …

Enabling conversational interaction with mobile ui using large language models

B Wang, G Li, Y Li - Proceedings of the 2023 CHI Conference on Human …, 2023 - dl.acm.org
Conversational agents show the promise to allow users to interact with mobile devices using
language. However, to perform diverse UI tasks with natural language, developers typically …

Anglekindling: Supporting journalistic angle ideation with large language models

S Petridis, N Diakopoulos, K Crowston… - Proceedings of the …, 2023 - dl.acm.org
News media often leverage documents to find ideas for stories, while being critical of the
frames and narratives present. Developing angles from a document such as a press release …

Who validates the validators? aligning llm-assisted evaluation of llm outputs with human preferences

S Shankar, JD Zamfirescu-Pereira… - Proceedings of the 37th …, 2024 - dl.acm.org
Due to the cumbersome nature of human evaluation and limitations of code-based
evaluation, Large Language Models (LLMs) are increasingly being used to assist humans in …