A Deep User Interface for Exploring LLaMa

Divya Perumal, Swaroop Panda

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The growing popularity and widespread adoption of large language models (LLMs) necessitates the development of tools that enhance the effectiveness of user interactions with these models. Understanding the structures and functions of these models poses a significant challenge for users. Visual analytics-driven tools enables users to explore and compare, facilitating better decision-making. This paper presents a visual analytics-driven tool equipped with interactive controls for key hyperparameters, including top-p, frequency and presence penalty, enabling users to explore, examine and compare the outputs of LLMs. In a user study, we assessed the tool’s effectiveness, which received favorable feedback for its visual design, with particular commendation for the interface layout and ease of navigation. Additionally, the feedback provided valuable insights for enhancing the effectiveness of Human-LLM interaction tools.

Original languageEnglish
Title of host publicationBCS HCI '25
Subtitle of host publicationProceedings of the 38th International BCS Human-Computer Interaction Conference
EditorsNervo Verdezoto Dias, Daniel J. Finnegan
Place of PublicationSwindon, UK
PublisherACM
Pages401-405
Number of pages5
DOIs
Publication statusPublished - 13 Nov 2025
EventBCS HCI 2025: Human Centred Approaches and their Impact on AI system design, application, and evaluation - Cardiff University, Cardiff, United Kingdom
Duration: 9 Nov 202511 Nov 2025
https://www.britchi2025.co.uk/
https://users.cs.cf.ac.uk/FinneganD/hci-2025/

Publication series

NameBCS Learning & Development
PublisherACM
ISSN (Electronic)1477-9358

Conference

ConferenceBCS HCI 2025
Abbreviated titleBCS HCI 2025
Country/TerritoryUnited Kingdom
CityCardiff
Period9/11/2511/11/25
Internet address

Keywords

  • Explainable AI
  • Hyperparameters
  • Large Language Models
  • User Interface
  • Visual Analytics

Cite this