Many people browse online communities to learn from others’ experiences and opinions, e.g., for constructing travel plans. Conversational search powered by large language models (LLMs) could ease this information-seeking task, but it remains under-investigated within the online community. In this paper, we first conducted an exploratory study (N=10) that indicated the helpfulness of a classic conversational search tool and identified room for improvement. Then, we proposed ConSearcher, an LLM-powered tool with dynamically generated member personas based on user queries to facilitate conversational search in the community. In ConSearcher, users can clarify their interests by checking what a simulated member similar to them may ask and get responses from diverse members’ perspectives. A within-subjects study (N=27) showed that compared to two conversational search baselines, ConSearcher led to significantly higher information-seeking outcome and user engagement but raised concerns about over-personalization. We discuss implications for supporting conversational information seeking in online communities.

Large language model (LLM)-based multi-agent systems have demonstrated impressive capabilities in handling complex tasks. However, the complexity of agentic behaviors makes these systems difficult to understand. When failures occur, developers often struggle to identify root causes and to determine actionable paths for improvement. Traditional methods that rely on inspecting raw log records are inefficient, given both the large volume and complexity of data. To address this challenge, we propose a framework and an interactive system, DiLLS, designed to reveal and structure the behaviors of multi-agent systems. The key idea is to organize information across three levels of query completion: activities, actions, and operations. By probing the multi-agent system through natural language, DiLLS derives and organizes information about planning and execution into a structured, multi-layered summary. Through a user study, we show that DiLLS significantly improves developers’ effectiveness and efficiency in identifying, diagnosing, and understanding failures in LLM-based multi-agent systems.

Hospital admission interviews are critical for patient care but strain nurses' capacity due to time constraints and staffing shortages. While LLM-powered conversational agents (CAs) offer automation potential, their rigid sequencing and lack of humanized communication skills risk misunderstandings and incomplete data capture. Through participatory design with clinicians and volunteers, we identified essential communication strategies and developed a novel CA that implements these strategies through: (1) dynamic topic management using graph-based conversation flows, and (2) context-aware scaffolding with few-shot prompt tuning. Technical evaluation on an admission interview dataset showed our system achieving performance comparable to or surpassing human-written ground truth, while outperforming prompt-engineered baselines. A between-subject study (N=44) demonstrated significantly improved user experience and data collection accuracy compared to existing solutions. We contribute a framework for humanizing medical CAs by translating clinician expertise into algorithmic strategies, alongside empirical insights for balancing efficiency and empathy in healthcare interactions, and considerations for generalizability.

Locomotion is a fundamental interaction in Virtual Reality (VR). Current locomotion methods, such as redirected walking, walking-in-place, and teleportation, make use of limited physical space and interaction mapping. However, there remains significant potential for improvement, particularly in reducing equipment burden and enhancing immersion. To locate these limitations, we rethink the procedure of VR walking interaction through the Human Information Processing paradigm. Finding that the peripherals' requirements and potential conflict in artificially designed interaction mappings are the bottlenecks in bridging intention and action, we developed MyGO, an AI-assisted locomotion prediction method. MyGO predicts users' future trajectories from their subtle movements, collected only by a VR headset, using a multitask learning (MTL) model. The proposed model demonstrates competitive results in both dataset validation and real-time studies. The code is available at https://github.com/ZichengLiu-seu/basic-MyGO.

Online mental health communities (OMHCs) offer rich posts and comments for viewers, who do not directly participate in the communications, to seek social support from others' experience. However, viewers could face challenges in finding helpful posts and comments and digesting the content to get needed support, as revealed in our formative study (N=10). In this work, we present an interactive visual tool named ComViewer to help viewers seek social support in OMHCs. With ComViewer , viewers can filter posts of different topics and find supportive comments via a zoomable circle packing visual component that adapts to searched keywords. Powered by LLM, ComViewer supports an interactive sensemaking process by enabling viewers to interactively highlight, summarize, and question any community content. A within-subjects study (N=20) demonstrates ComViewer's strengths in providing viewers with a more simplified, more fruitful, and more engaging support-seeking experience compared to a baseline OMHC interface without ComViewer . We further discuss design implications for facilitating information-seeking and sense making in online mental health communities.

Designing synthetic routes for novel molecules is pivotal in various fields like medicine and chemistry. In this process, researchers need to explore a set of synthetic reactions to transform starting molecules into intermediates step by step until the target novel molecule is obtained. However, designing synthetic routes presents challenges for researchers. First, researchers need to make decisions among numerous possible synthetic reactions at each step, considering various criteria (e.g., yield, experimental duration, and the count of experimental steps) to construct the synthetic route. Second, they must consider the potential impact of one choice at each step on the overall synthetic route. To address these challenges, we proposed SynthLens, a visual analytics system to facilitate the iterative construction of synthetic routes by exploring multiple possibilities for synthetic reactions at each step of construction. Specifically, we have introduced a tree-form visualization in SynthLensto compare and evaluate all the explored routes at various exploration steps, considering both the exploration step and multiple criteria. Our system empowers researchers to consider their construction process comprehensively, guiding them toward promising exploration directions to complete the synthetic route. We validated the usability and effectiveness of SynthLensthrough a quantitative evaluation and expert interviews, highlighting its role in facilitating the design process of synthetic routes. Finally, we discussed the insights of SynthLensto inspire other multi-criteria decision-making scenarios with visual analytics.

In AI-assisted decision-making, it is crucial but challenging for humans to achieve appropriate reliance on AI. This paper approaches this problem from a human-centered perspective, “human self-confidence calibration”. We begin by proposing an analytical framework to highlight the importance of calibrated human self-confidence. In our first study, we explore the relationship between human self-confidence appropriateness and reliance appropriateness. Then in our second study, We propose three calibration mechanisms and compare their effects on humans’ self-confidence and user experience. Subsequently, our third study investigates the effects of self-confidence calibration on AI-assisted decision-making. Results show that calibrating human self-confidence enhances human-AI team performance and encourages more rational reliance on AI (in some aspects) compared to uncalibrated baselines. Finally, we discuss our main findings and provide implications for designing future AI-assisted decision-making interfaces.

Preference-based learning aims to align robot task objectives with human values. One of the most common methods to infer human preferences is by pairwise comparisons of robot task trajectories. Traditional comparison-based preference labeling systems seldom support labelers to digest and identify critical differences between complex trajectories recorded in videos. Our formative study (N = 12) suggests that individuals may overlook non-salient task features and establish biased preference criteria during their preference elicitation process because of partial observations. In addition, they may experience mental fatigue when given many pairs to compare, causing their label quality to deteriorate. To mitigate these issues, we propose FARPLS, a Feature-Augmented Robot trajectory Preference Labeling System. FARPLS highlights potential outliers in a wide variety of task features that matter to humans and extracts the corresponding video keyframes for easy review and comparison. It also dynamically adjusts the labeling order according to users’ familiarities, difficulties of the trajectory pair, and level of disagreements. At the same time, the system monitors labelers’ consistency and provides feedback on labeling progress to keep labelers engaged. A between-subjects study (N = 42, 105 pairs of robot pick-and-place trajectories per person) shows that FARPLS can help users establish preference criteria more easily and notice more relevant details in the presented trajectories than the conventional interface. FARPLS also improves labeling consistency and engagement, mitigating challenges in preference elicitation without raising cognitive loads significantly.

In this study, we compare the virtual and real gait parameters to investigate the effect of appearances of embodied avatars and virtual reality experience on gait in physical and virtual environments. We developed a virtual environment simulation and gait detection system for analyzing gait. The system transfers real-life scenarios into a realistic presentation in the virtual environment and provides look-alike same-age and old-age avatars for participants. We conducted an empirical study and used subjective questionnaires to evaluate participants' feelings about the virtual reality experience. Also, the paired sample t-test and neural network were implemented to analyze gait differences. The results suggest that there are disparities in gait between virtual and real environments. Also, the appearance of embodied avatars could influence the gait parameters in the virtual environment. Moreover, the experience of embodying old-age avatars affects the gait in the real world.

Interdisciplinary studies often require researchers to explore literature in diverse branches of knowledge. Yet, navigating through the highly scattered knowledge from unfamiliar disciplines poses a significant challenge. In this paper, we introduce DiscipLink, a novel interactive system that facilitates collaboration between researchers and large language models (LLMs) in interdisciplinary information seeking (IIS). Based on users’ topic of interest, DiscipLink initiates exploratory questions from the perspectives of possible relevant fields of study, and users can further tailor these questions. DiscipLink then supports users in searching and screening papers under selected questions by automatically expanding queries with disciplinary-specific terminologies, extracting themes from retrieved papers, and highlighting the connections between papers and questions. Our evaluation, comprising a within-subject comparative experiment and an open-ended exploratory study, reveals that DiscipLink can effectively support researchers in breaking down disciplinary boundaries and integrating scattered knowledge in diverse fields. The findings underscore the potential of LLM-powered tools in fostering information-seeking practices and bolstering interdisciplinary research.

In healthcare, AI techniques are widely used for tasks like risk assessment and anomaly detection. Despite AI’s potential as a valuable assistant, its role in complex medical data analysis often over-simplifies human-AI collaboration dynamics. To address this, we collaborated with a local hospital, engaging six physicians and one data scientist in a formative study. From this collaboration, we propose a framework integrating two-phase interactive visualization systems: one for Human-Led, AI-Assisted Retrospective Analysis and another for AI-Mediated, Human-Reviewed Iterative Modeling. This framework aims to enhance understanding and discussion around effective human-AI collaboration in healthcare.

Choice of color is critical to creating effective charts with an engaging, enjoyable, and informative reading experience. However, designing a good color palette for a chart is a challenging task for novice users who lack related design expertise. For example, they often find it difficult to articulate their abstract intentions and translate these intentions into effective editing actions to achieve a desired outcome. In this work, we present NL2Color, a tool that allows novice users to refine chart color palettes using natural language expressions of their desired outcomes. We first collected and categorized a dataset of 131 triplets, each consisting of an original color palette of a chart, an editing intent, and a new color palette designed by human experts according to the intent. Our tool employs a large language model (LLM) to substitute the colors in original palettes and produce new color palettes by selecting some of the triplets as few-shot prompts. To evaluate our tool, we conducted a comprehensive two-stage evaluation, including a crowd-sourcing study ( N=71) and a within-subjects user study ( N=12). The results indicate that the quality of the color palettes revised by NL2Color has no significantly large difference from those designed by human experts. The participants who used NL2Color obtained revised color palettes to their satisfaction in a shorter period and with less effort.

In AI-assisted decision-making, it is critical for human decision-makers to know when to trust AI and when to trust themselves. However, prior studies calibrated human trust only based on AI confidence indicating AI’s correctness likelihood (CL) but ignored humans’ CL, hindering optimal team decision-making. To mitigate this gap, we proposed to promote humans’ appropriate trust based on the CL of both sides at a task-instance level. We first modeled humans’ CL by approximating their decision-making models and computing their potential performance in similar instances. We demonstrated the feasibility and effectiveness of our model via two preliminary studies. Then, we proposed three CL exploitation strategies to calibrate users’ trust explicitly/implicitly in the AI-assisted decision-making process. Results from a between-subjects experiment (N=293) showed that our CL exploitation strategies promoted more appropriate human trust in AI, compared with only using AI confidence. We further provided practical implications for more human-compatible AI-assisted decision-making.

Multi-step retrosynthetic route planning (MRRP) is the core task in synthetic chemistry, in which chemists recursively deconstruct a target molecule to find a set of reactants that make up the target. MRRP is challenging in that the search space is vast, and chemists are often lost in the process. Existing AI models can achieve automatic MRRP fast, but they only work on relatively simple targets, which leaves complex molecules under chemists’ expertise. To facilitate MRRP of complex molecules, we proposed a human-AI collaborative system, RetroLens, through a participatory design process. AI can contribute by two approaches: joint action and algorithm-in-the-loop. Deconstruction steps are allocated to chemists or AI based on their capabilities and AI recommends candidate revision steps to fix problems along the way. A within-subjects study (N=18) showed that chemists who used RetroLens reported faster MRRP, broader design space exploration, higher confidence in their planning, and lower cognitive load.

Existing research on human-AI collaborative decision-making focuses mainly on the interaction between AI and individual decision-makers. There is a limited understanding of how AI may perform in group decision-making. This paper presents a wizard-of-oz study in which two participants and an AI form a committee to rank three English essays. One novelty of our study is that we adopt a speculative design by endowing AI equal power to humans in group decision-making. We enable the AI to discuss and vote equally with other human members. We find that although the voice of AI is considered valuable, AI still plays a secondary role in the group because it cannot fully follow the dynamics of the discussion and make progressive contributions. Moreover, the divergent opinions of our participants regarding an “equal AI” shed light on the possible future of human-AI relations.

Online fandom communities (OFCs) provide a convenient space for fans to create, collect, and discuss the content of their mutual interest (e.g., music artists). Real-world events could frequently attract outsiders to join OFCs, providing both the opportunity to expand the fan base and challenges to manage the community. However, it is unclear that how influxes of newcomers would influence the development of OFCs and what user behaviors may be correlated with their future engagement. To fill this gap, we took the music OFCs as the focus, and quantitatively analyzed user behaviors and their correlations with users' future engagement in the community. Results suggested that 1) event-induced newcomers expressed more hate speech and negative sentiment, praised less celebrity-related content (e.g., song, album), and interacted with narrower cohorts than existing members; 2) Although existing members tended to receive more upvotes during the events than before and after the events, newcomers showed an opposite trend; 3) keeping users' activeness, expressing positive sentiments, and having diverse interactions during periods of influx were helpful when maintaining members' future levels of engagement. This work deepened the understanding of fan behaviors in the dynamic period, and we discussed how our insights could benefit OFCs.

Interdisciplinary experimental science (e.g., medicinal chemistry) refers to the disciplines that integrate knowledge from different scientific backgrounds and involve experiments in the research process. Deciding "in what direction to proceed" is critical for the success of the research in such disciplines, since the time, money, and resource costs of the subsequent research steps depend largely on this decision. However, such a direction identification task is challenging in that researchers need to integrate information from large-scale, heterogeneous materials from all associated disciplines and summarize the related publications of which the core contributions are often showcased in diverse formats. The task also requires researchers to estimate the feasibility and potential in future experiments in the selected directions. In this work, we selected medicinal chemistry as a case and presented an interactive visual tool, MedChemLens, to assist medicinal chemists in choosing their intended directions of research. This task is also known as drug target (i.e., disease-linked proteins) selection. Given a candidate target name, MedChemLens automatically extracts the molecular features of drug compounds from chemical papers and clinical trial records, organizes them based on the drug structures, and interactively visualizes factors concerning subsequent experiments. We evaluated MedChemLens through a within-subjects study (N=16). Compared with the control condition (i.e., unrestricted online search without using our tool), participants who only used MedChemLens reported faster search, better-informed selections, higher confidence in their selections, and lower cognitive load.

It is challenging for customers to select appearance building products (e.g., skincare products, weight loss programs) that suit them personally as such products usually demonstrate efficacy only after long-term usage. Although e-retailers generally provide product descriptions or other customers’ reviews, users often find it hard to relate to their own situations. In this work, we proposed a pipeline to display envisioned users’ appearance after long-term use of appearance building products to deliver their efficacy on each individual visually. We selected skincare as a case and developed SkincareMirror which predicts skincare effects on users’ facial images by analyzing product function labels, efficacy ratings, and skin models’ images. The results of a between-subjects study (N=48) show that (1) SkincareMirror outperforms the baseline shopping site in terms of perceived usability, usefulness, user satisfaction and helps users select products faster; (2) SkincareMirror is especially effective to males and users with limited product domain knowledge.

Food-posting, a pervasive practice on social media platforms, opens a window for introspection on personal food intake, physical health, and mental well-being. Existing self-reflection tools on food intake usually require manual logging of dietary information and inadequately support retrospective reviews beyond the data. To facilitate in-depth, non-judgmental self-reflection on information hidden in food-posting, we propose a design to transform general food posts into "a postcard from a past food journey". The postcards are procedurally created from food posts, and encode nutritional values together with the user's emotional status extracted from photos and texts. After validating the visual design, we evaluate the auto-generated postcards with 20 participants to explore how they reflect on the data, context, action, and value subjects. Qualitative feedback indicates that our designs encourage users to review their physical and mental well-being differently from conventional visualization. We conclude by discussing issues identified with the non-judgmental postcard design.