Large-scale text-to-image generation models for visual artists' creative works
Large-scale Text-to-image Generation Models (LTGMs)(eg, DALL-E), self-supervised deep
learning models trained on a huge dataset, have demonstrated the capacity for generating …
learning models trained on a huge dataset, have demonstrated the capacity for generating …
Foundation models meet visualizations: Challenges and opportunities
Recent studies have indicated that foundation models, such as BERT and GPT, excel at
adapting to various downstream tasks. This adaptability has made them a dominant force in …
adapting to various downstream tasks. This adaptability has made them a dominant force in …
Co-writing screenplays and theatre scripts with language models: Evaluation by industry professionals
Language models are increasingly attracting interest from writers. However, such models
lack long-range semantic coherence, limiting their usefulness for longform creative writing …
lack long-range semantic coherence, limiting their usefulness for longform creative writing …
Understanding the benefits and challenges of deploying conversational AI leveraging large language models for public health intervention
Recent large language models (LLMs) have advanced the quality of open-ended
conversations with chatbots. Although LLM-driven chatbots have the potential to support …
conversations with chatbots. Although LLM-driven chatbots have the potential to support …
Enabling conversational interaction with mobile ui using large language models
Conversational agents show the promise to allow users to interact with mobile devices using
language. However, to perform diverse UI tasks with natural language, developers typically …
language. However, to perform diverse UI tasks with natural language, developers typically …
Re3: Generating longer stories with recursive reprompting and revision
We consider the problem of automatically generating longer stories of over two thousand
words. Compared to prior work on shorter stories, long-range plot coherence and relevance …
words. Compared to prior work on shorter stories, long-range plot coherence and relevance …
Anglekindling: Supporting journalistic angle ideation with large language models
News media often leverage documents to find ideas for stories, while being critical of the
frames and narratives present. Developing angles from a document such as a press release …
frames and narratives present. Developing angles from a document such as a press release …
Leveraging large language models to power chatbots for collecting user self-reported data
Large language models (LLMs) provide a new way to build chatbots by accepting natural
language prompts. Yet, it is unclear how to design prompts to power chatbots to carry on …
language prompts. Yet, it is unclear how to design prompts to power chatbots to carry on …
Large language models are few-shot health learners
Large language models (LLMs) can capture rich representations of concepts that are useful
for real-world tasks. However, language alone is limited. While existing LLMs excel at text …
for real-world tasks. However, language alone is limited. While existing LLMs excel at text …
Choice over control: How users write with large language models using diegetic and non-diegetic prompting
We propose a conceptual perspective on prompts for Large Language Models (LLMs) that
distinguishes between (1) diegetic prompts (part of the narrative, eg “Once upon a time, I …
distinguishes between (1) diegetic prompts (part of the narrative, eg “Once upon a time, I …