Large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks. Understanding how LLMs internally represent knowledge remains a significant challenge. Despite Sparse Autoencoders (SAEs) have emerged as a promising technique for extracting interpretable features from LLMs, SAE features do not inherently align with human-understandable concepts, making their interpretation cumbersome and labor-intensive. To bridge the gap between SAE features and human concepts, we present ConceptViz, a visual analytics system designed for exploring concepts in LLMs. ConceptViz implements a novel Identification ⇒ Interpretation ⇒Validation pipeline, enabling users to query SAEs using concepts of interest, interactively explore concept-to-feature alignments, and validate the correspondences through model behavior verification. We demonstrate the effectiveness of ConceptViz through two usage scenarios and a user study. Our results show that ConceptViz enhances interpretability research by streamlining the discovery and validation of meaningful concept representations in LLMs, ultimately aiding researchers in building more accurate mental models of LLM features. Our code and user guide are publicly available at https://github.com/Happy-Hippo209/conceptViz.

The advent of Retrieval-Augmented Generation (RAG) has significantly enhanced the ability of Large Language Models (LLMs) to produce factually accurate and up-to-date responses. However, the performance of a RAG system is not determined by a single component but emerges from a complex interplay of modular choices, such as embedding models and retrieval algorithms. This creates a vast and often opaque configuration space, making it challenging for developers to understand performance trade-offs and identify optimal designs. To address this challenge, we present RAGExplorer, a visual analytics system for the systematic comparison and diagnosis of RAG configurations. RAGExplorer guides users through a seamless macro-to-micro analytical workflow. Initially, it empowers developers to survey the performance landscape across numerous configurations, allowing for a high-level understanding of which design choices are most effective. For a deeper analysis, the system enables users to drill down into individual failure cases, investigate how differences in retrieved information contribute to errors, and interactively test hypotheses by manipulating the provided context to observe the resulting impact on the generated answer. We demonstrate the effectiveness of RAGExplorer through detailed case studies and user studies, validating its ability to empower developers in navigating the complex RAG design space. Our code and user guide are publicly available at https://github.com/Thymezzz/RAGExplorer.

The emergence of quantum computers heralds a new frontier in computational power, empowering quantum algorithms to address challenges that defy classical computation. However, the design of quantum algorithms is challenging as it largely requires the manual efforts of quantum experts to transit mathematical expressions to quantum circuit diagrams. To ease this process, particularly for prototyping, educational, and modular design workflows, we propose to bridge the textual and visual contexts between mathematics and quantum circuits through visual linking and transitions. We contribute a design space for quantum algorithm design, focusing on the textual and visual elements, interactions, and design patterns throughout the quantum algorithm design process. Informed by the design space, we introduce QuRAFT, a visual interface that facilitates a seamless transition from abstract mathematical expressions to concrete quantum circuits. QuRAFT incorporates a suite of eight integrated visual and interaction designs tailored to support users in the formulation, implementation, and validation process of the quantum algorithm design. Through two detailed case studies and a user evaluation, this paper demonstrates the effectiveness of QuRAFT. Feedback from quantum computing experts highlights the practical utility of QuRAFT in algorithm design and provides valuable implications for future advancements in visualization and interaction design within the quantum computing domain.

Recent advances in large language models (LLMs) have shown great potential in automating the process of visualization authoring through simple natural language utterances. However, instructing LLMs using natural language is limited in precision and expressiveness for conveying visualization intent, leading to misinterpretation and time-consuming iterations. To address these limitations, we conduct an empirical study to understand how LLMs interpret ambiguous or incomplete text prompts in the context of visualization authoring, and the conditions making LLMs misinterpret user intent. Informed by the findings, we introduce visual prompts as a complementary input modality to text prompts, which help clarify user intent and improve LLMs' interpretation abilities. To explore the potential of multimodal prompting in visualization authoring, we design VisPilot, which enables users to easily create visualizations using multimodal prompts, including text, sketches, and direct manipulations on existing visualizations. We evaluate VisPilot through a controlled user study and an expert evaluation. The results suggest that multimodal prompts facilitate users in communicating spatial constraints, local references, and design preferences while maintaining comparable task efficiency to text-only prompting. We further discuss when text, visual, and hybrid prompts are beneficial for visualization authoring, and summarize design implications for future human-AI authoring systems.

The rapid development of large language models (LLMs), such as ChatGPT, has revolutionized the efficiency of creating programming tutorials. LLMs can be instructed with text prompts to generate comprehensive text descriptions for code snippets provided by users. However, the lack of transparency in the end-to-end generation process has hindered the understanding of model behavior and limited user control over the generated results. To tackle this challenge, we introduce a novel approach that breaks down the programming tutorial creation task into actionable steps. By employing the tree-of-thought method, LLMs engage in an exploratory process to generate diverse and faithful programming tutorials. We then present SPROUT, an authoring tool equipped with a series of interactive visualizations that empower users to have greater control and understanding of the programming tutorial creation process. A formal user study demonstrated the effectiveness of SPROUT, showing that our tool assists users to actively participate in the programming tutorial creation process, leading to more reliable and customizable results. By providing users with greater control and understanding, SPROUT enhances the user experience and improves the overall quality of programming tutorial.

Programming tutorials serve a crucial role in teaching coding and programming techniques. Creating high-quality programming tutorials remains a laborious task. Authors devote effort in writing step-by-step solutions, creating examples, and editing existing tutorials. We explore the potential of using the text-code connection to improve the authoring experience of programming tutorials. We proposed a mixed-initiative approach to infer, establish, and maintain the latent text-code connections. With a series of interactions, the STEP-LINK ( STEP- by-Step Tutorial Editing with Programmable LINK ages ) prototype leverages text-code connections to assist users in authoring tutorials. The results of our experiment demonstrate the effectiveness of our system in supporting users in the authoring of step-by-step code explanations, the creation of examples, and the iteration of tutorials.

Authoring graph visualization requires advanced programming skills, expert domain knowledge, and significant workload. Existing authoring tools either support limited templates of graph visualization, or suffer from a high learning cost. We analyze the design requirements on a tool for graph visualizations, and contribute Nuwa, a user-friendly declarative authoring tool for the interactive specification of graph visualizations in terms of data, entity, change, and encoding. Our implementation empowers users to conveniently create, compare, and modulate comprehensive graph visualizations with a wide range of styles. We showcase various examples to verify the expressiveness of Nuwa. Via an expert interview and the analysis on cognitive dimensions we evaluate the usability of Nuwa.

Advanced quantum computers have the capability to perform practical quantum computing to address specific problems that are intractable for classical computers. Nevertheless, these computers are susceptible to noise, leading to unexpectable errors in outcomes, which makes them less trustworthy. To address this challenge, we propose HammingVis, a visual analytics approach that helps identify and understand errors in quantum outcomes. Given that these errors exhibit latent structural patterns within Hamming space, we introduce two graph visualizations to reveal these patterns from distinct perspectives. One highlights the overall structure of errors, while the other focuses on the impact of errors within important subspaces. We further develop a prototype system for interactively exploring and discerning the correct outcomes within Hamming space. A novel design is presented to distinguish the neighborhood patterns between error and correct outcomes. The effectiveness of our approach is demonstrated through case studies involving two classic quantum algorithms’ outcome data.

Large language models (LLMs) like those that power OpenAI’s ChatGPT and Google’s Gemini have played a major part in the recent wave of machine learning and artificial intelligence advancements. However, interpreting LLMs and visualizing their components is extremely difficult due to the incredible scale and high dimensionality of model data. NeuronautLLM introduces a visual analysis system for identifying and visualizing influential neurons in transformer-based language models as they relate to user-defined prompts. Our approach combines simple, yet information-dense visualizations as well as neuron explanation and classification data to provide a wealth of opportunities for exploration. NeuronautLLM was reviewed by two experts to verify its efficacy as a tool for practical model interpretation. Interviews and usability tests with five LLM experts demonstrated NeuronautLLM’s exceptional usability and its readiness for real-world application. Furthermore, two in-depth case studies on model reasoning and social bias highlight NeuronautLLM’s versatility in aiding the analysis of a wide range of LLM research problems.

Quantum computing is a rapidly evolving field that enables exponential speed-up over classical algorithms. At the heart of this revolutionary technology are quantum circuits, which serve as vital tools for implementing, analyzing, and optimizing quantum algorithms. Recent advancements in quantum computing and the increasing capability of quantum devices have led to the development of more complex quantum circuits. However, traditional quantum circuit diagrams suffer from scalability and readability issues, which limit the efficiency of analysis and optimization processes. In this research, we propose a novel visualization approach for large-scale quantum circuits by adopting semantic analysis to facilitate the comprehension of quantum circuits. We first exploit meta-data and semantic information extracted from the underlying code of quantum circuits to create component segmentations and pattern abstractions, allowing for easier wrangling of massive circuit diagrams. We then develop Quantivine, an interactive system for exploring and understanding quantum circuits. A series of novel circuit visualizations is designed to uncover contextual details such as qubit provenance, parallelism, and entanglement. The effectiveness of Quantivine is demonstrated through two usage scenarios of quantum circuits with up to 100 qubits and a formal user evaluation with quantum experts. A free copy of this paper and all supplemental materials are available at https://osf.io/2m9yh/?view_only=0aa1618c97244f5093cd7ce15f1431f9.

Horizontal federated learning (HFL) enables distributed clients to train a shared model and keep their data privacy. In training high-quality HFL models, the data heterogeneity among clients is one of the major concerns. However, due to the security issue and the complexity of deep learning models, it is challenging to investigate data heterogeneity across different clients. To address this issue, based on a requirement analysis we developed a visual analytics tool, HetVis, for participating clients to explore data heterogeneity. We identify data heterogeneity through comparing prediction behaviors of the global federated model and the stand-alone model trained with local data. Then, a context-aware clustering of the inconsistent records is done, to provide a summary of data heterogeneity. Combining with the proposed comparison techniques, we develop a novel set of visualizations to identify heterogeneity issues in HFL. We designed three case studies to introduce how HetVis can assist client analysts in understanding different types of heterogeneity issues. Expert reviews and a comparative study demonstrate the effectiveness of HetVis.

Multiple-view (MV) representations enabling multi-perspective exploration of large and complex data are often employed on 2D displays. The technique also shows great potential in addressing complex analytic tasks in immersive visualization. However, although useful, the design space of MV representations in immersive visualization lacks in deep exploration. In this paper, we propose a new perspective to this line of research, by examining the effects of view layout for MV representations on situated analytics. Specifically, we disentangle situated analytics in perspectives of situatedness regarding spatial relationship between visual representations and physical referents, and analytics regarding cross-view data analysis including filtering, refocusing, and connecting tasks. Through an in-depth analysis of existing layout paradigms, we summarize design trade-offs for achieving high situatedness and effective analytics simultaneously. We then distill a list of design requirements for a desired layout that balances situatedness and analytics, and develop a prototype system with an automatic layout adaptation method to fulfill the requirements. The method mainly includes a cylindrical paradigm for egocentric reference frame, and a force-directed method for proper view-view, view-user, and view-referent proximities and high view visibility. We conducted a formal user study that compares layouts by our method with linked and embedded layouts. Quantitative results show that participants finished filtering- and connecting-centered tasks significantly faster with our layouts, and user feedback confirms high usability of the prototype system.