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 …
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 …
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 …
Beyond text generation: Supporting writers with continuous automatic text summaries
We propose a text editor to help users plan, structure and reflect on their writing process. It
provides continuously updated paragraph-wise summaries as margin annotations, using …
provides continuously updated paragraph-wise summaries as margin annotations, using …
Evallm: Interactive evaluation of large language model prompts on user-defined criteria
By simply composing prompts, developers can prototype novel generative applications with
Large Language Models (LLMs). To refine prototypes into products, however, developers …
Large Language Models (LLMs). To refine prototypes into products, however, developers …