paper-with-me

홈 › Papers

More Than "Means to an End": Supporting Reasoning with Transparently Designed AI Data Science Processes

2026-03-25 · Venkatesh Sivaraman, Patrick Vossler, Adam Perer, Julian Hong, Jean Feng arxiv

Generative artificial intelligence (AI) tools can now help people perform complex data science tasks regardless of their expertise. While these tools have great potential to help more people work with data, their end-to-end approach does not support users in evaluating alternative approaches and reformulating problems, both critical to solving open-ended tasks in high-stakes domains. In this paper, we reflect on two AI data science systems designed for the medical setting and how they function as tools for thought. We find that success in these systems was driven by constructing AI workflows around intentionally-designed intermediate artifacts, such as readable query languages, concept definitions, or input-output examples. Despite opaqueness in other parts of the AI process, these intermediates helped users reason about important analytical choices, refine their initial questions, and contribute their unique knowledge. We invite the HCI community to consider when and how intermediate artifacts should be designed to promote effective data science thinking.

📄 PDF Abstract BibTeX arXiv:2603.24877

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Hybrid Reasoning for Perception, Explanation, and Autonomous Action in Manufacturing

2025-06-10 · Christos Margadji, Sebastian W. Pattinson

Industrial processes must be robust and adaptable, as environments and tasks are often unpredictable, while operational errors remain costly and difficult to detect. AI-based control systems offer a path forward, yet typ…

Retrieval-augmented GenerationVision-Language-Action

Reasoning Is All You Need for Urban Planning AI

2025-11-07 · Sijie Yang, Jiatong Li, Filip Biljecki arxiv

AI has proven highly successful at urban planning analysis -- learning patterns from data to predict future conditions. The next frontier is AI-assisted decision-making: agents that recommend sites, allocate resources, a…

Model independent WWR for regulatory CVA and for accounting CVA and FVA

2020-03-06 · Chris Kenyon, Mourad Berrahoui, Benjamin Poncet

General wrong way risk (WWR) estimation is necessary for regulatory CVA capital and useful for pricing CVA and FVA. We introduce a model independent method for calculating WWR and update the definition of WWR to deal wit…

Navigating the Conceptual Multiverse

2026-04-20 · Andre Ye, Jenny Y. Huang, Alicia Guo, Rose Novick 외 arxiv

When language models answer open-ended problems, they implicitly make hidden decisions that shape their outputs, leaving users with uncontextualized answers rather than a working map of the problem; drawing on multiverse…

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

2026-05-23 · Jingchu Gai, Guanning Zeng, Christina Baek, Chen Wu 외 arxiv

Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require pr…

Reinforcement Learning