Results 1 to 10 of about 3,148,880 (368)
Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI [PDF]
Conference on Fairness, Accountability and Transparency, 2022 As research and industry moves towards large-scale models capable of numerous downstream tasks, the complexity of understanding multi-modal datasets that give nuance to models rapidly increases.
Mahima Pushkarna +2 more
semanticscholar +1 more source
Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models [PDF]
arXiv.org, 2023 Today, large language models (LLMs) are taught to use new tools by providing a few demonstrations of the tool's usage. Unfortunately, demonstrations are hard to acquire, and can result in undesirable biased usage if the wrong demonstration is chosen ...
Cheng-Yu Hsieh +7 more
semanticscholar +1 more source
, 2023 Yade is an extensible open-source framework for discrete numerical models, focused on the Discrete Element Method. The computation parts are written in c++ using a flexible object model and allowing independent implementation of new algorithms and ...
V. Šmilauer +26 more
semanticscholar +1 more source
Interactive Model Cards: A Human-Centered Approach to Model Documentation [PDF]
Conference on Fairness, Accountability and Transparency, 2022 Deep learning models for natural language processing (NLP) are increasingly adopted and deployed by analysts without formal training in NLP or machine learning (ML). However, the documentation intended to convey the model’s details and appropriate use is
Anamaria Crisan +3 more
semanticscholar +1 more source
Automatic Code Documentation Generation Using GPT-3 [PDF]
International Conference on Automated Software Engineering, 2022 Source code documentation is an important artifact for efficient software development. Code documentation could greatly benefit from automation since manual documentation is often labouring, resource and time-intensive.
Junaed Younus Khan, Gias Uddin
semanticscholar +1 more source
Collaboration Challenges in Building ML-Enabled Systems: Communication, Documentation, Engineering, and Process [PDF]
International Conference on Software Engineering, 2021 The introduction of machine learning (ML) components in software projects has created the need for software engineers to collabo-rate with data scientists and other specialists.
Nadia Nahar +3 more
semanticscholar +1 more source
JAMA Network Open, 2023 Key Points Question Can a large language model (LLM)-based chatbot outperform surgeons in generating readable, accurate, and complete procedure-specific risks, benefits, and alternatives (RBAs) for use in informed consent?
Hannah Decker +8 more
semanticscholar +1 more source
Understanding Machine Learning Practitioners' Data Documentation Perceptions, Needs, Challenges, and Desiderata [PDF]
Proc. ACM Hum. Comput. Interact., 2022 Data is central to the development and evaluation of machine learning (ML) models. However, the use of problematic or inappropriate datasets can result in harms when the resulting models are deployed.
A. Heger +4 more
semanticscholar +1 more source
DocTer: documentation-guided fuzzing for testing deep learning API functions [PDF]
International Symposium on Software Testing and Analysis, 2021 Input constraints are useful for many software development tasks. For example, input constraints of a function enable the generation of valid inputs, i.e., inputs that follow these constraints, to test the function deeper. API functions of deep learning (
Danning Xie +6 more
semanticscholar +1 more source
Documentation Matters: Human-Centered AI System to Assist Data Science Code Documentation in Computational Notebooks [PDF]
ACM Trans. Comput. Hum. Interact., 2021 Computational notebooks allow data scientists to express their ideas through a combination of code and documentation. However, data scientists often pay attention only to the code, and neglect creating or updating their documentation during quick ...
A. Wang +8 more
semanticscholar +1 more source