arXiv subjects

Bingsheng Yao

Publications and source records attributed to Bingsheng Yao.

At least 37 records · Page 2Linked to original sources

arXiv2025

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight

The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks from high-level intents, understanding how dark patterns affect agents is increasingly important. We present a two-phase empirical study examining how agents, human participants, and human-AI teams respond to 16 types of dark patterns across diverse scenarios. Phase 1 highlights that agents often fail to recognize dark patterns, and even when aware, prioritize task completion over protective action. Phase 2 revealed divergent failure modes: humans succumb due to cognitive shortcuts and habitual compliance, while agents falter from procedural blind spots. Human oversight improved avoidance but introduced costs such as attentional tunneling and cognitive load. Our findings show neither humans nor agents are uniformly resilient, and collaboration introduces new vulnerabilities, suggesting design needs for transparency, adjustable autonomy, and oversight.

cs.HC↗

arXiv2025

Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction

Recent advances in large language models (LLMs) have shown potential in clinical text summarization, but their ability to handle long patient trajectories with multi-modal data spread across time remains underexplored. This study systematically evaluates several state-of-the-art open-source LLMs, their Retrieval Augmented Generation (RAG) variants and chain-of-thought (CoT) prompting on long-context clinical summarization and prediction. We examine their ability to synthesize structured and unstructured Electronic Health Records (EHR) data while reasoning over temporal coherence, by re-engineering existing tasks, including discharge summarization and diagnosis prediction from two publicly available EHR datasets. Our results indicate that long context windows improve input integration but do not consistently enhance clinical reasoning, and LLMs are still struggling with temporal progression and rare disease prediction. While RAG shows improvements in hallucination in some cases, it does not fully address these limitations. Our work fills the gap in long clinical text summarization, establishing a foundation for evaluating LLMs with multi-modal data and temporal reasoning.

cs.CL↗

arXiv2025

SurgWound-Bench: A Benchmark for Surgical Wound Diagnosis

Surgical site infection (SSI) is one of the most common and costly healthcare-associated infections and and surgical wound care remains a significant clinical challenge in preventing SSIs and improving patient outcomes. While recent studies have explored the use of deep learning for preliminary surgical wound screening, progress has been hindered by concerns over data privacy and the high costs associated with expert annotation. Currently, no publicly available dataset or benchmark encompasses various types of surgical wounds, resulting in the absence of an open-source Surgical-Wound screening tool. To address this gap: (1) we present SurgWound, the first open-source dataset featuring a diverse array of surgical wound types. It contains 697 surgical wound images annotated by 3 professional surgeons with eight fine-grained clinical attributes. (2) Based on SurgWound, we introduce the first benchmark for surgical wound diagnosis, which includes visual question answering (VQA) and report generation tasks to comprehensively evaluate model performance. (3) Furthermore, we propose a three-stage learning framework, WoundQwen, for surgical wound diagnosis. In the first stage, we employ five independent MLLMs to accurately predict specific surgical wound characteristics. In the second stage, these predictions serve as additional knowledge inputs to two MLLMs responsible for diagnosing outcomes, which assess infection risk and guide subsequent interventions. In the third stage, we train a MLLM that integrates the diagnostic results from the previous two stages to produce a comprehensive report. This three-stage framework can analyze detailed surgical wound characteristics and provide subsequent instructions to patients based on surgical images, paving the way for personalized wound care, timely intervention, and improved patient outcomes.

cs.AI↗

arXiv2025

"Mango Mango, How to Let The Lettuce Dry Without A Spinner?": Exploring User Perceptions of Using An LLM-Based Conversational Assistant Toward Cooking Partner

The rapid advancement of Large Language Models (LLMs) has created numerous potentials for integration with conversational assistants (CAs) assisting people in their daily tasks, particularly due to their extensive flexibility. However, users' real-world experiences interacting with these assistants remain unexplored. In this research, we chose cooking, a complex daily task, as a scenario to explore people's successful and unsatisfactory experiences while receiving assistance from an LLM-based CA, Mango Mango. We discovered that participants value the system's ability to offer customized instructions based on context, provide extensive information beyond the recipe, and assist them in dynamic task planning. However, users expect the system to be more adaptive to oral conversation and provide more suggestive responses to keep them actively involved. Recognizing that users began treating our LLM-CA as a personal assistant or even a partner rather than just a recipe-reading tool, we propose five design considerations for future development.

cs.HC↗

arXiv2025

Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation

Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real human evaluator resources are often scarce and costly, the emerging "LLM-as-a-judge" paradigm sheds light on a promising approach to leverage LLM agents to believably simulate human evaluators. Yet, to date, existing LLM-as-a-judge approaches face two limitations: persona descriptions of agents are often arbitrarily designed, and the frameworks are not generalizable to other tasks. To address these challenges, we propose MAJ-EVAL, a Multi-Agent-as-Judge evaluation framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents (e.g., research papers), instantiate LLM agents with the personas, and engage in-group debates with multi-agents to Generate multi-dimensional feedback. Our evaluation experiments in both the educational and medical domains demonstrate that MAJ-EVAL can generate evaluation results that better align with human experts' ratings compared with conventional automated evaluation metrics and existing LLM-as-a-judge methods.

cs.CL↗

arXiv2025

UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design

Usability testing is a fundamental yet challenging (e.g., inflexible to iterate the study design flaws and hard to recruit study participants) research method for user experience (UX) researchers to evaluate a web design. Recent advances in Large Language Model-simulated Agent (LLM-Agent) research inspired us to design UXAgent to support UX researchers in evaluating and reiterating their usability testing study design before they conduct the real human subject study. Our system features an LLM-Agent module and a universal browser connector module so that UX researchers can automatically generate thousands of simulated users to test the target website. The results are shown in qualitative (e.g., interviewing how an agent thinks ), quantitative (e.g., # of actions), and video recording formats for UX researchers to analyze. Through a heuristic user evaluation with five UX researchers, participants praised the innovation of our system but also expressed concerns about the future of LLM Agent-assisted UX study.

cs.HC↗

arXiv2025

More Modality, More AI: Exploring Design Opportunities of AI-Based Multi-modal Remote Monitoring Technologies for Early Detection of Mental Health Sequelae in Youth Concussion Patients

Anxiety, depression, and suicidality are common mental health sequelae following concussion in youth patients, often exacerbating concussion symptoms and prolonging recovery. Despite the critical need for early detection of these mental health symptoms, clinicians often face challenges in accurately collecting patients' mental health data and making clinical decision-making in a timely manner. Today's remote patient monitoring (RPM) technologies offer opportunities to objectively monitor patients' activities, but they were not specifically designed for youth concussion patients; moreover, the large amount of data collected by RPM technologies may also impose significant workloads on clinicians to keep up with and use the data. To address these gaps, we employed a three-stage study consisting of a formative study, interface design, and design evaluation. We first conducted a formative study through semi-structured interviews with six highly professional concussion clinicians and identified clinicians' key challenges in remotely collecting patient information and accessing patient treatment compliance. Subsequently, we proposed preliminary clinician-facing interface designs with the integration of AI-based RPM technologies (AI-RPM), followed by design evaluation sessions with highly professional concussion clinicians. Clinicians underscored the value of integrating multi-modal AI-RPM technologies to support their decision-making while emphasizing the importance of customizable interfaces through collaborative design and multiple responsible design considerations.

cs.HC↗

arXiv2025

Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents

Role-Playing Agent (RPA) is an increasingly popular type of LLM Agent that simulates human-like behaviors in a variety of tasks. However, evaluating RPAs is challenging due to diverse task requirements and agent designs. This paper proposes an evidence-based, actionable, and generalizable evaluation design guideline for LLM-based RPA by systematically reviewing 1,676 papers published between Jan. 2021 and Dec. 2024. Our analysis identifies six agent attributes, seven task attributes, and seven evaluation metrics from existing literature. Based on these findings, we present an RPA evaluation design guideline to help researchers develop more systematic and consistent evaluation methods.

cs.HC↗

arXiv2025

Characterizing LLM-Empowered Personalized Story-Reading and Interaction for Children: Insights from Multi-Stakeholder Perspectives

Personalized interaction is highly valued by parents in their story-reading activities with children. While AI-empowered story-reading tools have been increasingly used, their abilities to support personalized interaction with children are still limited. Recent advances in large language models (LLMs) show promise in facilitating personalized interactions, but little is known about how to effectively and appropriately use LLMs to enhance children's personalized story-reading experiences. This work explores this question through a design-based study. Drawing on a formative study, we designed and developed StoryMate, an LLM-empowered personalized interactive story-reading tool for children, following an empirical study with children, parents, and education experts. Our participants valued the personalized features in StoryMate, and also highlighted the need to support personalized content, guiding mechanisms, reading context variations, and interactive interfaces. Based on these findings, we propose a series of design recommendations for better using LLMs to empower children's personalized story reading and interaction.

cs.HC↗

arXiv2025

CardioAI: A Multimodal AI-based System to Support Symptom Monitoring and Risk Detection of Cancer Treatment-Induced Cardiotoxicity

Despite recent advances in cancer treatments that prolong patients' lives, treatment-induced cardiotoxicity remains one severe side effect. The clinical decision-making of cardiotoxicity is challenging, as non-clinical symptoms can be missed until life-threatening events occur at a later stage, and clinicians already have a high workload centered on the treatment, not the side effects. Our project starts with a participatory design study with 11 clinicians to understand their practices and needs; then we build a multimodal AI system, CardioAI, that integrates wearables and LLM-powered voice assistants to monitor multimodal non-clinical symptoms. Also, the system includes an explainable risk prediction module that can generate cardiotoxicity risk scores and summaries as explanations to support clinicians' decision-making. We conducted a heuristic evaluation with four clinical experts and found that they all believe CardioAI integrates well into their workflow, reduces their information overload, and enables them to make more informed decisions.

cs.HC↗

arXiv2025

WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch

While just-in-time interventions (JITIs) have effectively targeted common health behaviors, individuals often have unique needs to intervene in personal undesirable actions that can negatively affect physical, mental, and social well-being. We present WatchGuardian, a smartwatch-based JITI system that empowers users to define custom interventions for these personal actions with a small number of samples. For the model to detect new actions based on limited new data samples, we developed a few-shot learning pipeline that finetuned a pre-trained inertial measurement unit (IMU) model on public hand-gesture datasets. We then designed a data augmentation and synthesis process to train additional classification layers for customization. Our offline evaluation with 26 participants showed that with three, five, and ten examples, our approach achieved an average accuracy of 76.8%, 84.7%, and 87.7%, and an F1 score of 74.8%, 84.2%, and 87.2% We then conducted a four-hour intervention study to compare WatchGuardian against a rule-based intervention. Our results demonstrated that our system led to a significant reduction by 64.0 +- 22.6% in undesirable actions, substantially outperforming the baseline by 29.0%. Our findings underscore the effectiveness of a customizable, AI-driven JITI system for individuals in need of behavioral intervention in personal undesirable actions. We envision that our work can inspire broader applications of user-defined personalized intervention with advanced AI solutions.

cs.HC↗

arXiv2025

SepsisCalc: Integrating Clinical Calculators into Early Sepsis Prediction via Dynamic Temporal Graph Construction

Sepsis is an organ dysfunction caused by a deregulated immune response to an infection. Early sepsis prediction and identification allow for timely intervention, leading to improved clinical outcomes. Clinical calculators (e.g., the six-organ dysfunction assessment of SOFA) play a vital role in sepsis identification within clinicians' workflow, providing evidence-based risk assessments essential for sepsis diagnosis. However, artificial intelligence (AI) sepsis prediction models typically generate a single sepsis risk score without incorporating clinical calculators for assessing organ dysfunctions, making the models less convincing and transparent to clinicians. To bridge the gap, we propose to mimic clinicians' workflow with a novel framework SepsisCalc to integrate clinical calculators into the predictive model, yielding a clinically transparent and precise model for utilization in clinical settings. Practically, clinical calculators usually combine information from multiple component variables in Electronic Health Records (EHR), and might not be applicable when the variables are (partially) missing. We mitigate this issue by representing EHRs as temporal graphs and integrating a learning module to dynamically add the accurately estimated calculator to the graphs. Experimental results on real-world datasets show that the proposed model outperforms state-of-the-art methods on sepsis prediction tasks. Moreover, we developed a system to identify organ dysfunctions and potential sepsis risks, providing a human-AI interaction tool for deployment, which can help clinicians understand the prediction outputs and prepare timely interventions for the corresponding dysfunctions, paving the way for actionable clinical decision-making support for early intervention.

cs.LG↗

arXiv2024

User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistants

Conventional Voice Assistants (VAs) rely on traditional language models to discern user intent and respond to their queries, leading to interactions that often lack a broader contextual understanding, an area in which Large Language Models (LLMs) excel. However, current LLMs are largely designed for text-based interactions, thus making it unclear how user interactions will evolve if their modality is changed to voice. In this work, we investigate whether LLMs can enrich VA interactions via an exploratory study with participants (N=20) using a ChatGPT-powered VA for three scenarios (medical self-diagnosis, creative planning, and discussion) with varied constraints, stakes, and objectivity. We observe that LLM-powered VA elicits richer interaction patterns that vary across tasks, showing its versatility. Notably, LLMs absorb the majority of VA intent recognition failures. We additionally discuss the potential of harnessing LLMs for more resilient and fluid user-VA interactions and provide design guidelines for tailoring LLMs for voice assistance.

cs.HC↗

arXiv2024

Secret Use of Large Language Model (LLM)

The advancements of Large Language Models (LLMs) have decentralized the responsibility for the transparency of AI usage. Specifically, LLM users are now encouraged or required to disclose the use of LLM-generated content for varied types of real-world tasks. However, an emerging phenomenon, users' secret use of LLM, raises challenges in ensuring end users adhere to the transparency requirement. Our study used mixed-methods with an exploratory survey (125 real-world secret use cases reported) and a controlled experiment among 300 users to investigate the contexts and causes behind the secret use of LLMs. We found that such secretive behavior is often triggered by certain tasks, transcending demographic and personality differences among users. Task types were found to affect users' intentions to use secretive behavior, primarily through influencing perceived external judgment regarding LLM usage. Our results yield important insights for future work on designing interventions to encourage more transparent disclosure of the use of LLMs or other AI technologies.

cs.HC↗

arXiv2024

"I Like Sunnie More Than I Expected!": Exploring User Expectation and Perception of an Anthropomorphic LLM-based Conversational Agent for Well-Being Support

The human-computer interaction (HCI) research community has a longstanding interest in exploring the mismatch between users' actual experiences and expectation toward new technologies, for instance, large language models (LLMs). In this study, we compared users' (N = 38) initial expectations against their post-interaction perceptions of two LLM-powered mental well-being intervention activity recommendation systems. Both systems have a built-in LLM to recommend a personalized well-being intervention activity, but one system (Sunnie) has an anthropomorphic conversational interaction design via elements such as appearance, persona, and natural conversation. Results showed that user engagement was high with both systems, and both systems exceeded users' expectations along the utility dimension, highlighting AI's potential to offer useful intervention activity recommendations. In addition, Sunnie further outperformed the non-anthropomorphic baseline system in relational warmth. These findings suggest that anthropomorphic conversational interaction design may be particularly effective in fostering warmth in mental health support contexts.

cs.HC↗

arXiv2024

StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children's Story-Based Learning

Interactive story reading is a common parent-child activity, where parents expect to teach both language skills and real-world knowledge beyond the story. While increasing storytelling and reading systems have been developed for this activity, they often fail to infuse real-world knowledge into the conversation. This limitation can be attributed to the existing question-answering (QA) datasets used for children's education, upon which the systems are built, failing to capture the nuances of how education experts think when conducting interactive story reading activities. To bridge this gap, we design an annotation framework, empowered by existing knowledge graph to capture experts' annotations and thinking process, and leverage this framework to construct StorySparkQA dataset, which comprises 5,868 expert-annotated QA pairs with real-world knowledge. We conduct automated and human expert evaluations across various QA pair generation settings to demonstrate that our StorySparkQA can effectively support models in generating QA pairs that target real-world knowledge beyond story content. StorySparkQA is available at https://huggingface.co/datasets/NEU-HAI/StorySparkQA.

cs.CL↗

arXiv2024

Human and LLM-Based Voice Assistant Interaction: An Analytical Framework for User Verbal and Nonverbal Behaviors

Recent progress in large language model (LLM) technology has significantly enhanced the interaction experience between humans and voice assistants (VAs). This project aims to explore a user's continuous interaction with LLM-based VA (LLM-VA) during a complex task. We recruited 12 participants to interact with an LLM-VA during a cooking task, selected for its complexity and the requirement for continuous interaction. We observed that users show both verbal and nonverbal behaviors, though they know that the LLM-VA can not capture those nonverbal signals. Despite the prevalence of nonverbal behavior in human-human communication, there is no established analytical methodology or framework for exploring it in human-VA interactions. After analyzing 3 hours and 39 minutes of video recordings, we developed an analytical framework with three dimensions: 1) behavior characteristics, including both verbal and nonverbal behaviors, 2) interaction stages--exploration, conflict, and integration--that illustrate the progression of user interactions, and 3) stage transition throughout the task. This analytical framework identifies key verbal and nonverbal behaviors that provide a foundation for future research and practical applications in optimizing human and LLM-VA interactions.

cs.HC↗

arXiv2024

Exploring Parent's Needs for Children-Centered AI to Support Preschoolers' Interactive Storytelling and Reading Activities

Interactive storytelling is vital for preschooler development. While children's interactive partners have traditionally been their parents and teachers, recent advances in artificial intelligence (AI) have sparked a surge of AI-based storytelling and reading technologies. As these technologies become increasingly ubiquitous in preschoolers' lives, questions arise regarding how they function in practical storytelling and reading scenarios and, how parents, the most critical stakeholders, experience and perceive these technologies. This paper investigates these questions through a qualitative study with 17 parents of children aged 3-6. Our findings suggest that even though AI-based storytelling and reading technologies provide more immersive and engaging interaction, they still cannot meet parents' expectations due to a series of interactive and algorithmic challenges. We elaborate on these challenges and discuss the possible implications of future AI-based interactive storytelling technologies for preschoolers.

cs.HC↗