Zheng Ning

This work builds on brushing and linking from data visualization and extends it to knowledge work. Knowledge workers frequently repurpose content across artifacts (e.g., creating a one‑page summary of a report and visuals for its presentation), yet the conceptual relationships between these representations are often implicit, placing a cognitive burden on knowledge workers to maintain alignment. We introduce interpretive linking, an approach that leverages generative AI to identify and highlight semantically related content across representations (brushing) and to interpret and propagate changes between them (linking). Rather than preserving strict correspondence, interpretive linking aims to maintain semantic coherence across formats and modalities. Using a research‑through‑design approach, we built a technology probe leveraging multiple models across textual and visual content and experimented with different strategies for managing semantic coherence. We then conducted a qualitative study with six knowledge workers, who used the probe to reflect on potential workflows. Participants generated 22 application concepts, ranging from responsive documents adapting to device form factor to collaborative tools supporting parallel work across modalities. Together, these findings surface design opportunities and open challenges for interpretive linking in knowledge work.

We present LACE, a hybrid Human-AI co-creative system integrated into Adobe Photoshop supporting turn-taking and parallel interaction modes for iterative image generation. Through a study with 21 participants across representational, abstract, and design tasks, we found turn-taking preferred in early stages for idea generation, and parallel modes suited for detailed refinement. While this shorter workshop paper provides key insights and highlights, the comprehensive findings and detailed analysis are presented in a longer version available separately on arXiv.

This paper introduces LACE, a co-creative system enabling professional artists to leverage generative AI through controlled prompting and iterative refinement within Photoshop. Addressing challenges in precision, iterative coherence, and workflow compatibility, LACE allows flexible control via layer-based editing and dual-mode collaboration (turn-taking and parallel). A pilot study (N=21) demonstrates significant improvements in user satisfaction, ownership, usability, and artistic perception compared to standard AI workflows. We offer comprehensive findings, system details, nuanced user feedback, and implications for integrating generative AI in professional art practices.

Querying structured databases with natural language (NL2SQL) has remained a difficult problem for years. Recently, the advancement of machine learning (ML), natural language processing (NLP), and large language models (LLM) have led to significant improvements in performance, with the best model achieving ∼85% percent accuracy on the benchmark Spider dataset. However, there is a lack of a systematic understanding of the types, causes, and effectiveness of error-handling mechanisms of errors for erroneous queries nowadays. To bridge the gap, a taxonomy of errors made by four representative NL2SQL models was built in this work, along with an in-depth analysis of the errors. Second, the causes of model errors were explored by analyzing the model-human attention alignment to the natural language query. Last, a within-subjects user study with 26 participants was conducted to investigate the effectiveness of three interactive error-handling mechanisms in NL2SQL. Findings from this article shed light on the design of model structure and error discovery and repair strategies for natural language data query interfaces in the future.

Video podcast teasers are short videos that can be shared on social media platforms to capture interest in full episodes of a video podcast. These teasers enable long-form podcasters to reach new audiences and gain more followers. However, creating a compelling teaser from an hour-long episode can be challenging. Selecting interesting clips requires significant mental effort; editing the chosen clips into a cohesive, well-produced teaser is time-consuming. To support the creation of video podcast teasers, we first investigated what makes a good teaser. We combined insights from audience comments and creator interviews to identify key ingredients. We also identified a common workflow used by creators during this process. Based on these findings, we developed a human-AI co-creative tool called PodReels to assist video podcasters in crafting teasers. Our user study demonstrated that PodReels significantly reduces creators’ mental demand and improves their efficiency in producing video podcast teasers.

Querying structured databases with natural language (NL2SQL) has remained a difficult problem for years. Recently, the advancement of machine learning (ML), natural language processing (NLP), and large language models (LLM) have led to significant improvements in performance, with the best model achieving ~85% percent accuracy on the benchmark Spider dataset. However, there is a lack of a systematic understanding of the types, causes, and effectiveness of error-handling mechanisms of errors for erroneous queries nowadays. To bridge the gap, a taxonomy of errors made by four representative NL2SQL models was built in this work, along with an in-depth analysis of the errors. Second, the causes of model errors were explored by analyzing the model-human attention alignment to the natural language query. Last, a within-subjects user study with 26 participants was conducted to investigate the effectiveness of three interactive error-handling mechanisms in NL2SQL. Findings from this paper shed light on the design of model structure and error discovery and repair strategies for natural language data query interfaces in the future.

Relational databases play an important role in business, science, and more. However, many users cannot fully unleash the analytical power of relational databases, because they are not familiar with database languages such as SQL. Many techniques have been proposed to automatically generate SQL from natural language, but they suffer from two issues: (1) they still make many mistakes, particularly for complex queries, and (2) they do not provide a flexible way for non-expert users to validate and refine incorrect queries. To address these issues, we introduce a new interaction mechanism that allows users to directly edit a step-by-step explanation of a query to fix errors. Our experiments on multiple datasets, as well as a user study with 24 participants, demonstrate that our approach can achieve better performance than multiple SOTA approaches. Our code and datasets are available at https://github.com/magic-YuanTian/STEPS.