Data Analysis in the Era of Generative AI

Chenglong Wang; Dan Marshall; Dave Brown; Gonzalo Ramos; Jeevana Priya Inala; Jianfeng Gao; Nathalie Riche; Steven Drucker; Victor Dibia

Data Analysis in the Era of Generative AI

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.18475 v1 pith:DHN3B6R5 submitted 2024-09-27 cs.AI cs.HC

Jeevana Priya Inala , Chenglong Wang , Steven Drucker , Gonzalo Ramos , Victor Dibia , Nathalie Riche , Dave Brown , Dan Marshall

show 1 more author

Jianfeng Gao

This is my paper · ORCID

classification cs.AIcs.HC

keywords analysisdatachallengesdesignuserworkflowacrossai-assisted

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

This paper explores the potential of AI-powered tools to reshape data analysis, focusing on design considerations and challenges. We explore how the emergence of large language and multimodal models offers new opportunities to enhance various stages of data analysis workflow by translating high-level user intentions into executable code, charts, and insights. We then examine human-centered design principles that facilitate intuitive interactions, build user trust, and streamline the AI-assisted analysis workflow across multiple apps. Finally, we discuss the research challenges that impede the development of these AI-based systems such as enhancing model capabilities, evaluating and benchmarking, and understanding end-user needs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Designing a Lightweight GenAI Interface for Visual Data Analysis
cs.HC 2025-09 reject novelty 4.0 of 10

A hybrid visual analysis tool where an LLM translates user intent into R model formulas and visualizations guide model checking, demonstrated on one example but not evaluated.
Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens
cs.CL 2025-06 reject novelty 3.0 of 10

DAP with 118.8M tokens improves a 70B LLM on cybersecurity benchmarks, but the claimed state-of-the-art data efficiency is not supported by the controlled comparisons.

Pith tools