no code implementations • 6 Mar 2023 • Hai Dang, Sven Goller, Florian Lehmann, Daniel Buschek
We propose a conceptual perspective on prompts for Large Language Models (LLMs) that distinguishes between (1) diegetic prompts (part of the narrative, e. g. "Once upon a time, I saw a fox..."), and (2) non-diegetic prompts (external, e. g. "Write about the adventures of the fox.").
no code implementations • 3 Sep 2022 • Hai Dang, Lukas Mecke, Florian Lehmann, Sven Goller, Daniel Buschek
Deep generative models have the potential to fundamentally change the way we create high-fidelity digital content but are often hard to control.
no code implementations • 19 Aug 2022 • Hai Dang, Karim Benharrak, Florian Lehmann, Daniel Buschek
As a key finding, the summaries gave users an external perspective on their writing and helped them to revise the content and scope of their drafted paragraphs.
no code implementations • 1 Aug 2022 • Florian Lehmann, Niklas Markert, Hai Dang, Daniel Buschek
2) Writing with suggestions, the AI suggests phrases and user selects from a list.
no code implementations • 2 Feb 2022 • Hai Dang, Lukas Mecke, Daniel Buschek
We found that more control dimensions (sliders) significantly increase task difficulty and user actions.
no code implementations • 1 Apr 2021 • Daniel Buschek, Lukas Mecke, Florian Lehmann, Hai Dang
This position paper examines potential pitfalls on the way towards achieving human-AI co-creation with generative models in a way that is beneficial to the users' interests.