Journal of Medical Internet ResearchBackgroundMedical texts present significant domain-specific challenges, and manually curating these texts is a time-consuming and labor-intensive process.
Rui Yang +18 more
doaj +2 more sources
Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation [PDF]
International Conference on Learning Analytics and Knowledge, 2023 Generative AI and large language models hold great promise in enhancing programming education by automatically generating individualized feedback for students.
Tung Phung +7 more
semanticscholar +1 more source
Visual Programming for Text-to-Image Generation and Evaluation [PDF]
arXiv.org, 2023 As large language models have demonstrated impressive performance in many domains, recent works have adopted language models (LMs) as controllers of visual modules for vision-and-language tasks.
Jaemin Cho, Abhaysinh Zala, Mohit Bansal
semanticscholar +1 more source
Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models [PDF]
AAAI Conference on Artificial Intelligence, 2023 Recently, Large Language Models (LLMs) have shown impressive abilities in code generation. However, existing LLMs' decoding strategies are designed for Natural Language (NL) generation, overlooking the differences between NL and programming languages (PL)
Yuqi Zhu +6 more
semanticscholar +1 more source
Fully Autonomous Programming with Large Language Models [PDF]
Annual Conference on Genetic and Evolutionary Computation, 2023 Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome": they tend to generate programs that semantically resemble the correct answer (as measured by text similarity metrics or human evaluation), but ...
Vadim Liventsev +3 more
semanticscholar +1 more source
CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming [PDF]
International Conference on Human Factors in Computing Systems, 2023 Natural language (NL) programming has become more approachable due to the powerful code-generation capability of large language models (LLMs). This shift to using NL to program enhances collaborative programming by reducing communication barriers and ...
Felicia Li Feng +5 more
semanticscholar +1 more source
Benchmarking Large Language Models for Automated Verilog RTL Code Generation [PDF]
Design, Automation and Test in Europe, 2022 Automating hardware design could obviate a signif-icant amount of human error from the engineering process and lead to fewer errors. Verilog is a popular hardware description language to model and design digital systems, thus generating Verilog code is a
Shailja Thakur +7 more
semanticscholar +1 more source
Private-Library-Oriented Code Generation with Large Language Models [PDF]
Knowledge-Based Systems, 2023 Large language models (LLMs), such as Codex and GPT-4, have recently showcased their remarkable code generation abilities, facilitating a significant boost in coding efficiency.
Daoguang Zan +8 more
semanticscholar +1 more source
In-IDE Code Generation from Natural Language: Promise and Challenges [PDF]
ACM Transactions on Software Engineering and Methodology, 2021 A great part of software development involves conceptualizing or communicating the underlying procedures and logic that needs to be expressed in programs.
Frank F. Xu +2 more
semanticscholar +1 more source
Automatic Data Visualization Generation from Chinese Natural Language Questions [PDF]
International Conference on Language Resources and Evaluation, 2023 Data visualization has emerged as an effective tool for getting insights from massive datasets. Due to the hardness of manipulating the programming languages of data visualization, automatic data visualization generation from natural languages (Text-to ...
Yan Ge +4 more
semanticscholar +1 more source