Graphologue: Exploring Large Language Model Responses with Interactive Diagrams

Jiang, Peiling; Rayan, Jude; Dow, Steven P.; Xia, Haijun

doi:10.1145/3586183.3606737

Cited by 16 publications

(5 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective is to tackle complex tasks, yet with enhanced control, customization, and precision. This is facilitated by employing visual programming techniques, such as chain designs [3,71,72] and mind maps [27,63,80], enabling a more interactive and user-defined reasoning framework. While there may be some overlap with other modes, such as Mode 2.2 UI for Varying Output, we classify this as a distinct submode due to its unique blend of reasoning and UI design.…”

Section: Mode 2: User Interface (Ui) Uer Interface (Figurementioning

confidence: 99%

“…The key strategy is to leverage various HCI techniques like visual programming and direct manipulation, to develop complex prompts. These prompts significantly enhance LLMs, equipping them with sophisticated capabilities for complex tasks, including argumentative writing [80], brainstorming [27,63], and more. However, they primarily focus on developing specific interaction modes, often overlooking a more comprehensive framework that encompasses various interaction perspectives.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration

Gao,

Gebreegziabher,

Choo

et al. 2024

Extended Abstracts of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

With ChatGPT's release, conversational prompting has become the most popular form of human-LLM interaction. However, its effectiveness is limited for more complex tasks involving reasoning, creativity, and iteration. Through a systematic analysis of HCI papers published since 2021, we identified four key phases in the human-LLM interaction flow-planning, facilitating, iterating, and testing-to precisely understand the dynamics of this process. Additionally, we have developed a taxonomy of four primary interaction modes: Mode 1: Standard Prompting, Mode 2: User Interface, Mode 3: Context-based, and Mode 4: Agent Facilitator. This taxonomy was further enriched using the "5W1H" guideline method, which involved a detailed examination of definitions, participant roles (Who), the phases that happened (When), human objectives and LLM abilities (What), and the mechanics of each interaction mode (How). We anticipate this taxonomy will contribute to the future design and evaluation of human-LLM interaction. CCS CONCEPTS• Human-centered computing → Natural language interfaces.

show abstract

Section: Mode 2: User Interface (Ui) Uer Interface (Figurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration

Gao,

Gebreegziabher,

Choo

et al. 2024

Extended Abstracts of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…• Task: David Zhou (team lead), Agnia Sergeyuk (team member), Jessi Stark (team member), Emad A. Alghamdi (team member), Sitong Wang (team member), Roy Pea (advisor) • User: Katy Ilonka Gero (team lead), Yewon Kim (team member), John Joon Young Chung (team member), Senjuti Dutta (team member), Lila Shroff (team member), Disha Shrivastava (team member), Eugenia H. Rho (advisor) integrated into the user's writing area (e.g., previewed in a light grey font color [41]) or can be selected from a pop-up list at the cursor [27,58,148]. Beyond linear text, further UI concepts include sketching [45] and views that arrange (generated) text on a 2D canvas, for example, as a graph [125] or post-it notes. 8 C.3 Ecosystem: Going from Micro-HCI to Macro-HCI Historical accounts of HCI [212,225] document how the definition of "the system" was first enlarged from the computer to include the human user, starting with attempts to apply psychological models of the individual human using a computer.…”

Section: A Author Contributionsmentioning

confidence: 99%

A Design Space for Intelligent and Interactive Writing Assistants

Lee,

Gero,

Chung

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to examine and explore the multidimensional space of intelligent and interactive writing assistants. Through a large community collaboration, we explore five aspects of writing assistants: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions (i.e., fundamental components of an aspect) and codes (i.e., potential options for each dimension) by systematically reviewing 115 papers. Our design space aims to offer researchers and designers a practical tool to navigate, comprehend, and compare the various possibilities of writing assistants, and aid in the envisioning and design of new writing assistants.

show abstract

“…However, unlike question answering over individual documents [82], the non-linear and dynamic workflows of sensemaking motivate exploration of a novel design space of human-LLM interactions. Recent work has shown LLM-powered applications can go beyond a linear, chat-like interaction paradigm, for instance by transposing text-based responses into flexible graphical representations [40], enabling recursive summarization [43], or supporting multilevel exploration of information [74].…”

Section: Human-llm Interactionmentioning

confidence: 99%

Marco: Supporting Business Document Workflows via Collection-Centric Information Foraging with Large Language Models

Fok,

Lipka,

Sun

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Knowledge workers often need to extract and analyze information from a collection of documents to solve complex information tasks in the workplace, e.g., hiring managers reviewing resumes or analysts assessing risk in contracts. However, foraging for relevant information can become tedious and repetitive over many documents and criteria of interest. We introduce Marco, a mixedinitiative workspace supporting sensemaking over diverse business document collections. Through collection-centric assistance, Marco reduces the cognitive costs of extracting and structuring information, allowing users to prioritize comparative synthesis and decision making processes. Users interactively communicate their information needs to an AI assistant using natural language and compose schemas that provide an overview of a document collection. Findings from a usability study (n=16) demonstrate that when using Marco, users complete sensemaking tasks 16% more quickly, with less effort, and without diminishing accuracy. A design probe with seven domain experts identifies how Marco can benefit various real-world workflows. CCS CONCEPTS• Human-centered computing → Interactive systems and tools.

show abstract

Graphologue: Exploring Large Language Model Responses with Interactive Diagrams

Cited by 16 publications

References 69 publications

A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration

A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration

A Design Space for Intelligent and Interactive Writing Assistants

Marco: Supporting Business Document Workflows via Collection-Centric Information Foraging with Large Language Models

Contact Info

Product

Resources

About