How Do Analysts Understand and Verify AI-Assisted Data Analyses?

September 19, 2023 Β· Declared Dead Β· πŸ› International Conference on Human Factors in Computing Systems

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Ken Gu, Ruoxi Shang, Tim Althoff, Chenglong Wang, Steven M. Drucker arXiv ID 2309.10947 Category cs.HC: Human-Computer Interaction Citations 39 Venue International Conference on Human Factors in Computing Systems Last Checked 3 months ago
Abstract
Data analysis is challenging as it requires synthesizing domain knowledge, statistical expertise, and programming skills. Assistants powered by large language models (LLMs), such as ChatGPT, can assist analysts by translating natural language instructions into code. However, AI-assistant responses and analysis code can be misaligned with the analyst's intent or be seemingly correct but lead to incorrect conclusions. Therefore, validating AI assistance is crucial and challenging. Here, we explore how analysts understand and verify the correctness of AI-generated analyses. To observe analysts in diverse verification approaches, we develop a design probe equipped with natural language explanations, code, visualizations, and interactive data tables with common data operations. Through a qualitative user study (n=22) using this probe, we uncover common behaviors within verification workflows and how analysts' programming, analysis, and tool backgrounds reflect these behaviors. Additionally, we provide recommendations for analysts and highlight opportunities for designers to improve future AI-assistant experiences.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Human-Computer Interaction

Died the same way β€” πŸ‘» Ghosted