Sensemaking with AI B

会議の名前
CHI 2024
Towards a Diffractive Analysis of Prompt-Based Generative AI
要旨

Recent developments in prompt-based generative AI has given rise to discourse surrounding the perceived ethical concerns, economic implications, and consequences for the future of cultural production. As generative imagery becomes pervasive in mainstream society, dominated primarily by emerging industry leaders, we encourage that the role of the CHI community be one of inquiry; to investigate the numerous ways in which generative AI has the potential to, and already is, augmenting human creativity. In this paper, we conducted a diffractive analysis exploring the potential role of prompt-based interfaces in artists' creative practice. Over a two week period, seven visual artists were given access to a personalised instance of Stable Diffusion, fine-tuned on a dataset of their work. In the following diffractive analysis, we identified two dominant modes adopted by participants, AI for ideation, and AI for production. We furthermore present a number of ethical design considerations for the future development of generative AI interfaces.

著者
Nina Rajcic
Monash University, Melbourne, VIC, Australia
Maria Teresa Llano Rodriguez
Monash University, Melbourne, Victoria, Australia
Jon McCormack
Monash University, Melbourne, Victoria, Australia
論文URL

https://doi.org/10.1145/3613904.3641971

動画
Where Are We So Far? Understanding Data Storytelling Tools from the Perspective of Human-AI Collaboration
要旨

Data storytelling is powerful for communicating data insights, but it requires diverse skills and considerable effort from human creators. Recent research has widely explored the potential for artificial intelligence (AI) to support and augment humans in data storytelling. However, there lacks a systematic review to understand data storytelling tools from the perspective of human-AI collaboration, which hinders researchers from reflecting on the existing collaborative tool designs that promote humans' and AI's advantages and mitigate their shortcomings. This paper investigated existing tools with a framework from two perspectives: the stages in the storytelling workflow where a tool serves, including analysis, planning, implementation, and communication, and the roles of humans and AI in each stage, such as creators, assistants, optimizers, and reviewers. Through our analysis, we recognize the common collaboration patterns in existing tools, summarize lessons learned from these patterns, and further illustrate research opportunities for human-AI collaboration in data storytelling.

受賞
Honorable Mention
著者
Haotian Li
The Hong Kong University of Science and Technology, Hong Kong, China
Yun Wang
Microsoft Research Asia, Beijing, China
Huamin Qu
The Hong Kong University of Science and Technology, Hong Kong, China
論文URL

https://doi.org/10.1145/3613904.3642726

動画
Dissecting users' needs for search result explanations
要旨

There is a growing demand for transparency in search engines to understand how search results are curated and to enhance users' trust. Prior research has introduced search result explanations with a focus on "how" to explain, assuming explanations are beneficial. Our study takes a step back to examine "if" search explanations are needed and "when" they are likely to provide benefits. Additionally, we summarize key characteristics of helpful explanations and share users' perspectives on explanation features provided by Google and Bing. Interviews with non-technical individuals reveal that users do not always seek or understand search explanations and mostly desire them for complex and critical tasks. They find Google's search explanations too obvious but appreciate the ability to contest search results. Based on our findings, we offer design recommendations for search engines and explanations to help users better evaluate search results and enhance their search experience.

著者
Prerna Juneja
Seattle University, Seattle, Washington, United States
Wenjuan Zhang
Dataminr, New York City, New York, United States
Alison Marie. Smith-Renner
Dataminr, New York, New York, United States
Hemank Lamba
Dataminr, New York, New York, United States
Joel Tetreault
Dataminr, New York, New York, United States
Alex Jaimes
Dataminr, New York, New York, United States
論文URL

https://doi.org/10.1145/3613904.3642059

動画
Natural Language Dataset Generation Framework for Visualizations Powered by Large Language Models
要旨

We introduce VL2NL, a Large Language Model (LLM) framework that generates rich and diverse NL datasets using Vega-Lite specifications as input, thereby streamlining the development of Natural Language Interfaces (NLIs) for data visualization. To synthesize relevant chart semantics accurately and enhance syntactic diversity in each NL dataset, we leverage 1) a guided discovery incorporated into prompting so that LLMs can steer themselves to create faithful NL datasets in a self-directed manner; 2) a score-based paraphrasing to augment NL syntax along with four language axes. We also present a new collection of 1,981 real-world Vega-Lite specifications that have increased diversity and complexity than existing chart collections. When tested on our chart collection, VL2NL extracted chart semantics and generated L1/L2 captions with 89.4% and 76.0% accuracy, respectively. It also demonstrated generating and paraphrasing utterances and questions with greater diversity compared to the benchmarks. Last, we discuss how our NL datasets and framework can be utilized in real-world scenarios. The codes and chart collection are available at https://github.com/hyungkwonko/chart-llm.

著者
Kwon Ko
KAIST, Daejeon, Korea, Republic of
Hyeon Jeon
Seoul National University, Seoul, Korea, Republic of
Gwanmo Park
Seoul National University, Seoul, Korea, Republic of
Dae Hyun Kim
KAIST, Daejeon, Korea, Republic of
Nam Wook Kim
Boston College, Chestnut Hill, Massachusetts, United States
Juho Kim
KAIST, Daejeon, Korea, Republic of
Jinwook Seo
Seoul National University, Seoul, Korea, Republic of
論文URL

https://doi.org/10.1145/3613904.3642943

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

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 mixed-initiative 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.

著者
Raymond Fok
University of Washington, Seattle, Washington, United States
Nedim Lipka
Adobe Systems , San Jose, California, United States
Tong Sun
Adobe Research, San Jose, California, United States
Alexa Siu
Adobe Research, San Jose, California, United States
論文URL

https://doi.org/10.1145/3613904.3641969

動画