Summary of Prompt Smells: An Omen For Undesirable Generative Ai Outputs, by Krishna Ronanki et al.
Prompt Smells: An Omen for Undesirable Generative AI Outputs
by Krishna Ronanki, Beatriz Cabrero-Daniel, Christian Berger
First submitted to arxiv on: 23 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Software Engineering (cs.SE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research proposes two novel concepts to address limitations in Generative Artificial Intelligence (GenAI). The authors focus on creating trustworthy AI models, which is crucial for applications like storytelling, illustration, and music composition. They define “desirability” as a key metric for evaluating GenAI outputs and identify three factors that influence it. Additionally, they introduce the concept of “prompt smells,” inspired by code smells in software development, which negatively impact desirability. This work aims to contribute to ongoing discussions about GenAI’s trustworthiness and advance the field. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making sure Artificial Intelligence (AI) creates things that are good and useful. Right now, AI can create stories, pictures, music, and more, but it often gets things wrong or makes stuff that isn’t very good. The authors of this paper want to fix this by coming up with new ideas for how we evaluate what AI produces. They also talk about “prompt smells” which are like bugs in software code that make AI produce bad results. This research is important because it helps us understand why AI can be unreliable and how we can make it better. |
Keywords
* Artificial intelligence * Prompt
