Visual Concept Programming: A Visual Analytics Approach to Injecting Human Intelligence at Scale

EvoVis: A Visual Analytics Method to Understand the Labeling Iterations in Data Programming

Obtaining high-quality labeled training data poses a significant bottleneck in the domain of machine learning. Data programming has emerged as a new paradigm to address this issue by converting human knowledge into labeling functions (LFs) to quickly produce low-cost probabilistic labels. To ensure the quality of labeled data, data programmers commonly iterate LFs for many rounds until satisfactory performance is achieved. However, the challenge in understanding the labeling iterations stems from interpreting the intricate relationships between data programming elements, exacerbated by their many-to-many and directed characteristics, inconsistent formats, and the large scale of data typically involved in labeling tasks. These complexities may impede the evaluation of label quality, identification of areas for improvement, and the effective optimization of LFs for acquiring high-quality labeled data. In this article, we introduce EvoVis, a visual analytics method for multi-class text labeling tasks. It seamlessly integrates relationship analysis and temporal overview to display contextual and historical information on a single screen, aiding in explaining the labeling iterations in data programming. We assessed its utility and effectiveness through case studies and user studies. The results indicate that EvoVis can effectively assist data programmers in understanding labeling iterations and improving the quality of labeled data, as evidenced by an increase of 0.16 in the average F1 score when compared to the default analysis tool.

LLM Comparator: Interactive Analysis of Side-by-Side Evaluation of Large Language Models

Evaluating large language models (LLMs) presents unique challenges. While automatic side-by-side evaluation, also known as LLM-as-a-judge, has become a promising solution, model developers and researchers face difficulties with scalability and interpretability when analyzing these evaluation outcomes. To address these challenges, we introduce LLM Comparator, a new visual analytics tool designed for side-by-side evaluations of LLMs. This tool provides analytical workflows that help users understand when and why one LLM outperforms or underperforms another, and how their responses differ. Through close collaboration with practitioners developing LLMs at Google, we have iteratively designed, developed, and refined the tool. Qualitative feedback from these users highlights that the tool facilitates in-depth analysis of individual examples while enabling users to visually overview and flexibly slice data. This empowers users to identify undesirable patterns, formulate hypotheses about model behavior, and gain insights for model improvement. LLM Comparator has been integrated into Google's LLM evaluation platforms and open-sourced.

Doom or Deliciousness: Challenges and Opportunities for Visualization in the Age of Generative Models

Generative text-to-image models (as exemplified by DALL-E, MidJourney, and Stable Diffusion) have recently made enormous technological leaps, demonstrating impressive results in many graphical domains-from logo design to digital painting to photographic composition. However, the quality of these results has led to existential crises in some fields of art, leading to questions about the role of human agency in the production of meaning in a graphical context. Such issues are central to visualization, and while these generative models have yet to be widely applied in visualization, it seems only a matter of time until their integration is manifest. Seeking to circumvent similar ponderous dilemmas, we attempt to understand the roles that generative models might play across visualization. We do so by constructing a framework that characterizes what these technologies offer at various stages of the visualization workflow, augmented and analyzed through semi-structured interviews with 21 experts from related domains. Through this work, we map the space of opportunities and risks that might arise in this intersection, identifying doomsday prophecies and delicious low-hanging fruits that are ripe for research.