Despite their increasing capabilities, text-to-image generative AI systems are known to produce biased, offensive, and otherwise problematic outputs. While recent advancements have supported testing and auditing of generative AI, existing auditing methods still face challenges in supporting effectively explore the vast space of AI-generated outputs in a structured way. To address this gap, we conducted formative studies with five AI auditors and synthesized five design goals for supporting systematic AI audits. Based on these insights, we developed Vipera, an interactive auditing interface that employs multiple visual cues including a scene graph to facilitate image sensemaking and inspire auditors to explore and hierarchically organize the auditing criteria. Additionally, Vipera leverages LLM-powered suggestions to facilitate exploration of unexplored auditing directions. Through a controlled experiment with 24 participants experienced in AI auditing, we demonstrate Vipera's effectiveness in helping auditors navigate large AI output spaces and organize their analyses while engaging with diverse criteria.

Web AI agents such as ChatGPT Agent and GenSpark are increasingly used for routine web-based tasks, yet they still rely on text-based input prompts, lack proactive detection of user intent, and offer no support for interactive data analysis and decision making. We present WebSeek, a mixed-initiative browser extension that enables users to discover and extract information from webpages to then flexibly build, transform, and refine tangible data artifacts–such as tables, lists, and visualizations–all within an interactive canvas. Within this environment, users can perform analysis–including data transformations such as joining tables or creating visualizations–while an in-built AI both proactively offers context-aware guidance and automation, and reactively responds to explicit user requests. An exploratory user study (N=15) with WebSeek as a probe reveals participants’ diverse analysis strategies, underscoring their desire for transparency and control during human-AI collaboration.

LLM-driven tools have significantly lowered barriers to writing SQL queries. However, user instructions are often underspecified, assuming the model understands implicit knowledge, such as dataset schemas, domain conventions, and task-specific requirements, that isn’t explicitly provided. This results in frequently erroneous scripts that require users to repeatedly clarify their intent. Additionally, users struggle to validate generated scripts because they cannot verify whether the model correctly applied implicit knowledge. We present Cerebra, an interactive NL-to-SQL tool that aligns implicit knowledge between users and LLMs during SQL authoring. Cerebra automatically retrieves implicit knowledge from historical SQL scripts based on user instructions, presents this knowledge in an interactive tree view for code review, and supports iterative refinement to improve generated scripts. To evaluate the effectiveness and usability of Cerebra, we conducted a user study with 16 participants, demonstrating its improved support for customized SQL authoring. The source code of Cerebra is available at https://github.com/zjuidg/CHI26-Cerebra.

Large Language Models (LLMs) demonstrate exceptional capabilities in factual question answering, yet they sometimes provide incorrect responses. To address this issue, knowledge editing techniques have emerged as effective methods for correcting factual information in LLMs. However, typical knowledge editing workflows struggle with identifying the optimal set of model layers for editing and rely on summary indicators that provide insufficient guidance. This lack of transparency hinders effective comparison and identification of optimal editing strategies. In this paper, we present KEditVis, a novel visual analytics system designed to assist users in gaining a deeper understanding of knowledge editing through interactive visualizations, improving editing outcomes, and discovering valuable insights for the future development of knowledge editing algorithms. With KEditVis, users can select appropriate layers as the editing target, explore the reasons behind ineffective edits, and perform more targeted and effective edits. Our evaluation, including usage scenarios, expert interviews, and a user study, validates the effectiveness and usability of the system.

Data profiling plays a critical role in understanding the structure of complex datasets and supporting numerous downstream tasks, such as social media analytics and financial fraud detection. While existing research predominantly focuses on structured data formats, a substantial portion of semi-structured textual data still requires ad-hoc and arduous manual profiling to extract and comprehend its internal structures. In this work, we propose StructVizor, an interactive profiling system that facilitates sensemaking and transformation of semi-structured textual data. Our tool mainly addresses two challenges: a) extracting and visualizing the diverse structural patterns within data, such as how information is organized or related, and b) enabling users to efficiently perform various wrangling operations on textual data. Through automatic data parsing and structure mining, StructVizor enables visual analytics of structural patterns, while incorporating novel interactions to enable profile-based data wrangling. A comparative user study involving 12 participants demonstrates the system's usability and its effectiveness in supporting exploratory data analysis and transformation tasks.

Data analysts frequently employ code completion tools in writing custom scripts to tackle complex tabular data wrangling tasks. However, existing tools do not sufficiently link the data contexts such as schemas and values with the code being edited. This not only leads to poor code suggestions, but also frequent interruptions in coding processes as users need additional code to locate and understand relevant data. We introduce Xavier, a tool designed to enhance data wrangling script authoring in computational notebooks. Xavier maintains users' awareness of data contexts while providing data-aware code suggestions. It automatically highlights the most relevant data based on the user's code, integrates both code and data contexts for more accurate suggestions, and instantly previews data transformation results for easy verification. To evaluate the effectiveness and usability of Xavier, we conducted a user study with 16 data analysts, showing its potential to streamline data wrangling scripts authoring.

This study investigates the trajectory tracking strategy of a snake robot with sideslip disturbance and unknown model parameters. To guide the robot to track the ideal trajectory faster and more accurately, an adaptive anti-sideslip strategy for a snake robot with the Integral Line-of-Sight (ILOS) function is reported. This technique eliminates direction sideslip and error fluctuation by using auxiliary integral terms and shortens the convergence time of state variables. Following the position and angle control objectives, the proposed controller considers the negative effects caused by the uncertainty and time variability of environmental parameters and compensates for the joint input using the adaptive update laws. The environment adaptability and tracking efficiency are improved. The stability analysis indicates that the state errors converge to the origin. The simulation and experiment data verifies the effectiveness and strength of the work.Note to Practitioners—This article was motivated by the problem of robust trajectory tracking for a snake robot in an environment with sideslip disturbance and unknown model parameters. In this environment, information of the motion space (for example, the coefficient of ground friction) cannot be obtained. In addition, there may be other system limitations (for example, motion sideslip limitations) and other operational limitations. These limitations are caused by the requirements of various common trajectory tracking objectives. These cases should also be considered in the control strategy. However, based on the existing methods of tracking control for snake robots, there is still a lack of a complete and reliable autonomous control scheme that can consider the above problems. On this basis, we present a reliable control strategy, which considers the above problems and the dynamic uncertainty of the model. In the future, we will extend the proposed method to the field of formation tracking control for multiple robots.

Plain tables excel at displaying data details and are widely used in data presentation, often polished to an elaborate appearance for readability in many scenarios. However, existing authoring tools fail to provide both flexible and efficient support for altering the table layout and styles, motivating us to develop an intuitive and swift tool for table prototyping. To this end, we contribute Table Illustrator, a table authoring system taking a novel visual metaphor, puzzle, as the primary interaction unit. Through combinations and configurations on puzzles, the system enables rapid table construction and supports a diverse range of table layouts and styles. The tool design is informed by practical challenges and requirements from interviews with 10 table practitioners and a structured design space based on an analysis of over 2,500 real-world tables. User studies showed that Table Illustrator achieved comparable performance to Microsoft Excel while reducing users’ completion time and perceived workload.

Tables are a ubiquitous data format for insight communication. However, transforming data into consumable tabular views remains a challenging and time-consuming task. To lower the barrier of such a task, research efforts have been devoted to developing interactive approaches for data transformation, but many approaches still presume that their users have considerable knowledge of various data transformation concepts and functions. In this study, we leverage natural language (NL) as the primary interaction modality to improve the accessibility of average users to performing complex data transformation and facilitate intuitive table generation and editing. Designing an NL-driven data transformation approach introduces two challenges: 1) NL-driven synthesis of interpretable pipelines and 2) incremental refinement of synthesized tables. To address these challenges, we present NL2Rigel, an interactive tool that assists users in synthesizing and improving tables from semi-structured text with NL instructions. Based on a large language model and prompting techniques, NL2Rigel can interpret the given NL instructions into a table synthesis pipeline corresponding to Rigel specifications, a declarative language for tabular data transformation. An intuitive interface is designed to visualize the synthesis pipeline and the generated tables, helping users understand the transformation process and refine the results efficiently with targeted NL instructions. The comprehensiveness of NL2Rigel is demonstrated with an example gallery, and we further confirmed NL2Rigel's usability with a comparative user study by showing that the task completion time with NL2Rigel is significantly shorter than that with the original version of Rigel with comparable completion rates.

We present Rigel, an interactive system for rapid transformation of tabular data. Rigel implements a new declarative mapping approach that formulates the data transformation procedure as direct mappings from data to the row, column, and cell channels of the target table. To construct such mappings, Rigel allows users to directly drag data attributes from input data to these three channels and indirectly drag or type data values in a spreadsheet, and possible mappings that do not contradict these interactions are recommended to achieve efficient and straightforward data transformation. The recommended mappings are generated by enumerating and composing data variables based on the row, column, and cell channels, thereby revealing the possibility of alternative tabular forms and facilitating open-ended exploration in many data transformation scenarios, such as designing tables for presentation. In contrast to existing systems that transform data by composing operations (like transposing and pivoting), Rigel requires less prior knowledge on these operations, and constructing tables from the channels is more efficient and results in less ambiguity than generating operation sequences as done by the traditional by-example approaches. User study results demonstrated that Rigel is significantly less demanding in terms of time and interactions and suits more scenarios compared to the state-of-the-art by-example approach. A gallery of diverse transformation cases is also presented to show the potential of Rigel's expressiveness.

Coverage-guided fuzzing has become mainstream in fuzzing to automatically expose program vulnerabilities. Recently, a group of fuzzers are proposed to adopt a random search mechanism namely Havoc, explicitly or implicitly, to augment their edge exploration. However, they only tend to adopt the default setup of Havoc as an implementation option while none of them attempts to explore its power under diverse setups or inspect its rationale for potential improvement. In this paper, to address such issues, we conduct the first empirical study on Havoc to enhance the understanding of its characteristics. Specifically, we first find that applying the default setup of Havoc to fuzzers can significantly improve their edge coverage performance. Interestingly, we further observe that even simply executing Havoc itself without appending it to any fuzzer can lead to strong edge coverage performance and outperform most of our studied fuzzers. Moreover, we also extend the execution time of Havoc and find that most fuzzers can not only achieve significantly higher edge coverage, but also tend to perform similarly (i.e., their performance gaps get largely bridged). Inspired by the findings, we further propose HavocMAB, which models the Havoc mutation strategy as a multi-armed bandit problem to be solved by dynamically adjusting the mutation strategy. The evaluation result presents that HavocMAB can significantly increase the edge coverage by 11.1% on average for all the benchmark projects compared with Havoc and even slightly outperform state-of-the-art QSYM which augments its computing resource by adopting three parallel threads. We further execute HavocMAB with three parallel threads and result in 9% higher average edge coverage over QSYM upon all the benchmark projects.