Graphologue: Exploring Large Language Model Responses with Interactive Diagrams
Informations
Type:
misc
Auteurs:
Peiling Jiang and Jude Rayan and Steven P. Dow and Haijun Xia
Pertinence:
Haute
Référence:
jiang2023graphologue
Doi:
Mots-clés:
Url:
https://arxiv.org/abs/2305.11473
Date de publication:
05/2023
Résumé:
chat + output des réponses du llm sous forme de diagram + menu contextuels pour en savoir plus
Abstract:
Large language models (LLMs) have recently soared in popularity due to their ease of access and the unprecedented intelligence exhibited on diverse applications. However, LLMs like ChatGPT present significant limitations in supporting complex information tasks due to the insufficient affordances of the text-based medium and linear conversational structure. Through a formative study with ten participants, we found that LLM interfaces often present long-winded responses, making it difficult for people to quickly comprehend and interact flexibly with various pieces of information, particularly during more complex tasks. We present Graphologue, an interactive system that converts text-based responses from LLMs into graphical diagrams to facilitate information-seeking and question-answering tasks. Graphologue employs novel prompting strategies and interface designs to extract entities and relationships from LLM responses and constructs node-link diagrams in real-time. Further, users can interact with the diagrams to flexibly adjust the graphical presentation and to submit context-specific prompts to obtain more information. Utilizing diagrams, Graphologue enables graphical, non-linear dialogues between humans and LLMs, facilitating information exploration, organization, and comprehension.
Pdf:
Lien pdf
Références
0 articles
Titre Type Pertinence Auteurs Date Publication Références Citations Actions
Pas encore d'article
Citations
0 articles
Titre Type Pertinence Auteurs Date Publication Références Citations Actions
Pas encore d'article
Mots-clés
0 mots-clés
Nom Nombre d'articles Actions
Pas encore de mot-clé
Auteurs
1 auteurs
Nom Nombre d'articles Actions
Peiling Jiang and Jude Rayan and Steven P. Dow and Haijun Xia 1