Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387635284> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4387635284 abstract "Text entry is an essential task in our day-to-day digital interactions. Numerous intelligent features have been developed to streamline this process, making text entry more effective, efficient, and fluid. These improvements include sentence prediction and user personalization. However, as deep learning-based language models become the norm for these advanced features, the necessity for data collection and model fine-tuning increases. These challenges can be mitigated by harnessing the in-context learning capability of large language models such as GPT-3.5. This unique feature allows the language model to acquire new skills through prompts, eliminating the need for data collection and fine-tuning. Consequently, large language models can learn various text prediction techniques. We initially showed that, for a sentence prediction task, merely prompting GPT-3.5 surpassed a GPT-2 backed system and is comparable with a fine-tuned GPT-3.5 model, with the latter two methods requiring costly data collection, fine-tuning and post-processing. However, the task of prompting large language models to specialize in specific text prediction tasks can be challenging, particularly for designers without expertise in prompt engineering. To address this, we introduce Promptor, a conversational prompt generation agent designed to engage proactively with designers. Promptor can automatically generate complex prompts tailored to meet specific needs, thus offering a solution to this challenge. We conducted a user study involving 24 participants creating prompts for three intelligent text entry tasks, half of the participants used Promptor while the other half designed prompts themselves. The results show that Promptor-designed prompts result in a 35% increase in similarity and 22% in coherence over those by designers." @default.
- W4387635284 created "2023-10-14" @default.
- W4387635284 creator A5000662703 @default.
- W4387635284 creator A5042452579 @default.
- W4387635284 creator A5068640497 @default.
- W4387635284 creator A5070594684 @default.
- W4387635284 creator A5072139873 @default.
- W4387635284 date "2023-10-12" @default.
- W4387635284 modified "2023-10-15" @default.
- W4387635284 title "Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques" @default.
- W4387635284 doi "https://doi.org/10.48550/arxiv.2310.08101" @default.
- W4387635284 hasPublicationYear "2023" @default.
- W4387635284 type Work @default.
- W4387635284 citedByCount "0" @default.
- W4387635284 crossrefType "posted-content" @default.
- W4387635284 hasAuthorship W4387635284A5000662703 @default.
- W4387635284 hasAuthorship W4387635284A5042452579 @default.
- W4387635284 hasAuthorship W4387635284A5068640497 @default.
- W4387635284 hasAuthorship W4387635284A5070594684 @default.
- W4387635284 hasAuthorship W4387635284A5072139873 @default.
- W4387635284 hasBestOaLocation W43876352841 @default.
- W4387635284 hasConcept C105795698 @default.
- W4387635284 hasConcept C107457646 @default.
- W4387635284 hasConcept C133462117 @default.
- W4387635284 hasConcept C136764020 @default.
- W4387635284 hasConcept C137293760 @default.
- W4387635284 hasConcept C151730666 @default.
- W4387635284 hasConcept C154945302 @default.
- W4387635284 hasConcept C162324750 @default.
- W4387635284 hasConcept C183003079 @default.
- W4387635284 hasConcept C187736073 @default.
- W4387635284 hasConcept C199360897 @default.
- W4387635284 hasConcept C204321447 @default.
- W4387635284 hasConcept C2777530160 @default.
- W4387635284 hasConcept C2779343474 @default.
- W4387635284 hasConcept C2780451532 @default.
- W4387635284 hasConcept C33923547 @default.
- W4387635284 hasConcept C41008148 @default.
- W4387635284 hasConcept C86803240 @default.
- W4387635284 hasConcept C98045186 @default.
- W4387635284 hasConceptScore W4387635284C105795698 @default.
- W4387635284 hasConceptScore W4387635284C107457646 @default.
- W4387635284 hasConceptScore W4387635284C133462117 @default.
- W4387635284 hasConceptScore W4387635284C136764020 @default.
- W4387635284 hasConceptScore W4387635284C137293760 @default.
- W4387635284 hasConceptScore W4387635284C151730666 @default.
- W4387635284 hasConceptScore W4387635284C154945302 @default.
- W4387635284 hasConceptScore W4387635284C162324750 @default.
- W4387635284 hasConceptScore W4387635284C183003079 @default.
- W4387635284 hasConceptScore W4387635284C187736073 @default.
- W4387635284 hasConceptScore W4387635284C199360897 @default.
- W4387635284 hasConceptScore W4387635284C204321447 @default.
- W4387635284 hasConceptScore W4387635284C2777530160 @default.
- W4387635284 hasConceptScore W4387635284C2779343474 @default.
- W4387635284 hasConceptScore W4387635284C2780451532 @default.
- W4387635284 hasConceptScore W4387635284C33923547 @default.
- W4387635284 hasConceptScore W4387635284C41008148 @default.
- W4387635284 hasConceptScore W4387635284C86803240 @default.
- W4387635284 hasConceptScore W4387635284C98045186 @default.
- W4387635284 hasLocation W43876352841 @default.
- W4387635284 hasOpenAccess W4387635284 @default.
- W4387635284 hasPrimaryLocation W43876352841 @default.
- W4387635284 hasRelatedWork W1499005795 @default.
- W4387635284 hasRelatedWork W1582019636 @default.
- W4387635284 hasRelatedWork W2070126461 @default.
- W4387635284 hasRelatedWork W2466832359 @default.
- W4387635284 hasRelatedWork W2593798266 @default.
- W4387635284 hasRelatedWork W3040708694 @default.
- W4387635284 hasRelatedWork W3098003361 @default.
- W4387635284 hasRelatedWork W3172493050 @default.
- W4387635284 hasRelatedWork W4385420271 @default.
- W4387635284 hasRelatedWork W2109940557 @default.
- W4387635284 isParatext "false" @default.
- W4387635284 isRetracted "false" @default.
- W4387635284 workType "article" @default.