Designing LLM chains by adapting techniques from crowdsourcing workflows
LLM chains enable complex tasks by decomposing work into a sequence of sub-tasks.
Crowdsourcing workflows similarly decompose complex tasks into smaller tasks for human …
Crowdsourcing workflows similarly decompose complex tasks into smaller tasks for human …
[HTML][HTML] Large language models meet user interfaces: The case of provisioning feedback
Abstract Incorporating Generative Artificial Intelligence (GenAI), especially Large Language
Models (LLMs), into educational settings presents valuable opportunities to boost the …
Models (LLMs), into educational settings presents valuable opportunities to boost the …
Prompts are programs too! understanding how developers build software containing prompts
The introduction of generative pre-trained models, like GPT-4, has introduced a
phenomenon known as prompt engineering, whereby model users repeatedly write and …
phenomenon known as prompt engineering, whereby model users repeatedly write and …
Content-Centric Prototyping of Generative AI Applications: Emerging Approaches and Challenges in Collaborative Software Teams
Generative AI models are increasingly powering software applications, offering the
capability to produce expressive content across varied contexts. However, unlike previous …
capability to produce expressive content across varied contexts. However, unlike previous …
Exploring Prompt Engineering Practices in the Enterprise
M Desmond, M Brachman - arXiv preprint arXiv:2403.08950, 2024 - arxiv.org
Interaction with Large Language Models (LLMs) is primarily carried out via prompting. A
prompt is a natural language instruction designed to elicit certain behaviour or output from a …
prompt is a natural language instruction designed to elicit certain behaviour or output from a …
A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration
With ChatGPT's release, conversational prompting has become the most popular form of
human-LLM interaction. However, its effectiveness is limited for more complex tasks …
human-LLM interaction. However, its effectiveness is limited for more complex tasks …
Development in times of hype: How freelancers explore Generative AI?
The rise of generative AI has led many companies to hire freelancers to harness its potential.
However, this technology presents unique challenges to developers who have not …
However, this technology presents unique challenges to developers who have not …
Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks
The potential of using Large Language Models (LLMs) themselves to evaluate LLM outputs
offers a promising method for assessing model performance across various contexts …
offers a promising method for assessing model performance across various contexts …
[PDF][PDF] Automatic Smart Contract Generation Through LLMs: When The Stochastic Parrot Fails
Abstract Blockchain and Artificial Intelligence (AI) have revolutionized the technology
landscape, evolving predominantly along parallel trajectories. This research investigates the …
landscape, evolving predominantly along parallel trajectories. This research investigates the …
Enhancing the shopping experience in e-commerce: a path to improvement–buy the best
This research paper presents the development of" Buy by Best," a user-friendly platform
designed to save users' time by providing a consolidated shopping experience. The project …
designed to save users' time by providing a consolidated shopping experience. The project …