Bingsheng Yao

Ying Xu, Dakuo Wang, Mo Yu et al. · cmu

Question answering (QA) is a fundamental means to facilitate assessment and training of narrative comprehension skills for both machines and young children, yet there is scarcity of high-quality QA datasets carefully designed to serve this purpose. In particular, existing datasets rarely distinguish fine-grained reading skills, such as the understanding of varying narrative elements. Drawing on the reading education research, we introduce FairytaleQA, a dataset focusing on narrative comprehension of kindergarten to eighth-grade students. Generated by educational experts based on an evidence-based theoretical framework, FairytaleQA consists of 10,580 explicit and implicit questions derived from 278 children-friendly stories, covering seven types of narrative elements or relations. Our dataset is valuable in two folds: First, we ran existing QA models on our dataset and confirmed that this annotation helps assess models' fine-grained learning skills. Second, the dataset supports question generation (QG) task in the education domain. Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.

Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran et al. · amazon-science, cmu

Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using leaderboards, but the evaluation choices become sub-optimal as better alternatives arise. This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims. To make following best model evaluation practices easier, we introduce GEMv2. The new version of the Generation, Evaluation, and Metrics Benchmark introduces a modular infrastructure for dataset, model, and metric developers to benefit from each others work. GEMv2 supports 40 documented datasets in 51 languages. Models for all datasets can be evaluated online and our interactive data card creation and rendering tools make it easier to add new datasets to the living benchmark.

Zhiping Zhang, Michelle Jia, Hao-Ping Lee et al. · cmu

The widespread use of Large Language Model (LLM)-based conversational agents (CAs), especially in high-stakes domains, raises many privacy concerns. Building ethical LLM-based CAs that respect user privacy requires an in-depth understanding of the privacy risks that concern users the most. However, existing research, primarily model-centered, does not provide insight into users' perspectives. To bridge this gap, we analyzed sensitive disclosures in real-world ChatGPT conversations and conducted semi-structured interviews with 19 LLM-based CA users. We found that users are constantly faced with trade-offs between privacy, utility, and convenience when using LLM-based CAs. However, users' erroneous mental models and the dark patterns in system design limited their awareness and comprehension of the privacy risks. Additionally, the human-like interactions encouraged more sensitive disclosures, which complicated users' ability to navigate the trade-offs. We discuss practical design guidelines and the needs for paradigm shifts to protect the privacy of LLM-based CA users.

Matthew Pisano, Peter Ly, Abraham Sanders et al.

Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment still fail to fully prevent harmful responses when models are deliberately attacked. Such vulnerabilities can lead to LLMs being manipulated into generating hazardous content: from instructions for creating dangerous materials to inciting violence or endorsing unethical behaviors. To help mitigate this issue, we introduce Bergeron: a framework designed to improve the robustness of LLMs against attacks without any additional parameter fine-tuning. Bergeron is organized into two tiers; with a secondary LLM acting as a guardian to the primary LLM. This framework better safeguards the primary model against incoming attacks while monitoring its output for any harmful content. Empirical analysis reviews that by using Bergeron to complement models with existing alignment training, we can significantly improve the robustness and safety of multiple, commonly used commercial and open-source LLMs. Specifically, we found that models integrated with Bergeron are, on average, nearly seven times more resistant to attacks compared to models without such support.

Jiaju Chen, Bo Sun, Yuxuan Lu et al.

Multi-agent systems (MAS) built on large language models have shown growing promise, with their effectiveness resting on agents' ability to coordinate through text-based channels much as human teams do. Yet recent study suggests that MAS often falter not because agents lack individual task-solving ability, but because they lack collaborative competence: the capacity to establish common ground, maintain shared task understanding, balance individual and collective incentives, and repair misalignment as interaction unfolds. Decades of research in Computer-Supported Cooperative Work have characterized these requirements for human teams coordinating under constrained communication, yet existing MAS evaluations focus mainly on task outcomes or single-agent proficiency in reasoning, planning, and tool use. To enable a systematic analysis of agents' collaborative competence in MAS, we introduce CollabSim, a configurable simulation framework that combines a theory-grounded definition of collaborative capabilities, controlled manipulation of interaction conditions, and action-level probing of agents' internal states. Experiments across four LLMs show that CollabSim can capture condition effects, separate model performance patterns, and reveal task-dependent effects of agent design.

Jiaju Chen, Yuxuan Lu, Jiayi Su et al.

Recent advances in LLM agents have enabled complex cognitive capabilities, such as multi-step reasoning, planning, and tool use, that increasingly position these agents as human collaborators. Effective collaboration, however, requires collaborators to continuously maintain and align mental models of their own reasoning,partners' intentions, and shared goals during the collaborative process. Today's agents rarely develop such capabilities since they are primarily optimized for task completion, and the community lacks authentic human collaboration data with action-level mental model annotations that could guide agents toward process-level collaborative competence. To bridge this gap, we present ALMANAC, a dataset of Action-Level Mental model ANnotations for Agent Collaboration built from the Map Task, a classic dyadic routing task from social science. ALMANAC contains 2,987 collaboration actions, each paired with theory-informed mental model annotations that record the participants' self-reasoning, perceived partner intent, and perceived team goal. We benchmark six LLMs on predicting humans' next-turn behavior and mental models. Our results demonstrate ALMANAC's utility in evaluating models' ability to simulate human collaborative behaviors and infer their underlying mental models.

Xuhai Xu, Bingsheng Yao, Yuanzhe Dong et al.

Advances in large language models (LLMs) have empowered a variety of applications. However, there is still a significant gap in research when it comes to understanding and enhancing the capabilities of LLMs in the field of mental health. In this work, we present a comprehensive evaluation of multiple LLMs on various mental health prediction tasks via online text data, including Alpaca, Alpaca-LoRA, FLAN-T5, GPT-3.5, and GPT-4. We conduct a broad range of experiments, covering zero-shot prompting, few-shot prompting, and instruction fine-tuning. The results indicate a promising yet limited performance of LLMs with zero-shot and few-shot prompt designs for mental health tasks. More importantly, our experiments show that instruction finetuning can significantly boost the performance of LLMs for all tasks simultaneously. Our best-finetuned models, Mental-Alpaca and Mental-FLAN-T5, outperform the best prompt design of GPT-3.5 (25 and 15 times bigger) by 10.9% on balanced accuracy and the best of GPT-4 (250 and 150 times bigger) by 4.8%. They further perform on par with the state-of-the-art task-specific language model. We also conduct an exploratory case study on LLMs' capability on mental health reasoning tasks, illustrating the promising capability of certain models such as GPT-4. We summarize our findings into a set of action guidelines for potential methods to enhance LLMs' capability for mental health tasks. Meanwhile, we also emphasize the important limitations before achieving deployability in real-world mental health settings, such as known racial and gender bias. We highlight the important ethical risks accompanying this line of research.

Bingsheng Yao, Guiming Chen, Ruishi Zou et al.

While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can not we design and leverage multiple prompts together to further improve the LLM's performance? In this work, we propose In-Context Sampling (ICS), a low-resource LLM prompting technique to produce confident predictions by optimizing the construction of multiple ICL prompt inputs. Extensive experiments with three open-source LLMs (FlanT5-XL, Mistral-7B, and Mixtral-8x7B) on four NLI datasets (e-SNLI, Multi-NLI, ANLI, and Contract-NLI) and one QA dataset (CommonsenseQA) illustrate that ICS can consistently enhance LLMs' performance. An in-depth evaluation with three data similarity-based ICS strategies suggests that these strategies can further elevate LLM's performance, which sheds light on a new yet promising future research direction.

Jiaju Chen, Yuxuan Lu, Shao Zhang et al.

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.

Changchang Yin, Pin-Yu Chen, Bingsheng Yao et al.

Sepsis is the leading cause of in-hospital mortality in the USA. Early sepsis onset prediction and diagnosis could significantly improve the survival of sepsis patients. Existing predictive models are usually trained on high-quality data with few missing information, while missing values widely exist in real-world clinical scenarios (especially in the first hours of admissions to the hospital), which causes a significant decrease in accuracy and an increase in uncertainty for the predictive models. The common method to handle missing values is imputation, which replaces the unavailable variables with estimates from the observed data. The uncertainty of imputation results can be propagated to the sepsis prediction outputs, which have not been studied in existing works on either sepsis prediction or uncertainty quantification. In this study, we first define such propagated uncertainty as the variance of prediction output and then introduce uncertainty propagation methods to quantify the propagated uncertainty. Moreover, for the potential high-risk patients with low confidence due to limited observations, we propose a robust active sensing algorithm to increase confidence by actively recommending clinicians to observe the most informative variables. We validate the proposed models in both publicly available data (i.e., MIMIC-III and AmsterdamUMCdb) and proprietary data in The Ohio State University Wexner Medical Center (OSUWMC). The experimental results show that the propagated uncertainty is dominant at the beginning of admissions to hospitals and the proposed algorithm outperforms state-of-the-art active sensing methods. Finally, we implement a SepsisLab system for early sepsis prediction and active sensing based on our pre-trained models. Clinicians and potential sepsis patients can benefit from the system in early prediction and diagnosis of sepsis.

Xiangyang Mou, Mo Yu, Bingsheng Yao et al. · ibm-research

Pre-trained Transformer models have achieved successes in a wide range of NLP tasks, but are inefficient when dealing with long input sequences. Existing studies try to overcome this challenge via segmenting the long sequence followed by hierarchical encoding or post-hoc aggregation. We propose a synchronization mechanism for hierarchical encoding. Our approach first identifies anchor tokens across segments and groups them by their roles in the original input sequence. Then inside Transformer layer, anchor embeddings are synchronized within their group via a self-attention module. Our approach is a general framework with sufficient flexibility -- when adapted to a new task, it is easy to be enhanced with the task-specific anchor definitions. Experiments on two representative tasks with different types of long input texts, NarrativeQA summary setting and wild multi-hop reasoning from HotpotQA, demonstrate that our approach is able to improve the global information exchange among segments while maintaining efficiency.

Shao Zhang, Jianing Yu, Xuhai Xu et al.

Today's AI systems for medical decision support often succeed on benchmark datasets in research papers but fail in real-world deployment. This work focuses on the decision making of sepsis, an acute life-threatening systematic infection that requires an early diagnosis with high uncertainty from the clinician. Our aim is to explore the design requirements for AI systems that can support clinical experts in making better decisions for the early diagnosis of sepsis. The study begins with a formative study investigating why clinical experts abandon an existing AI-powered Sepsis predictive module in their electrical health record (EHR) system. We argue that a human-centered AI system needs to support human experts in the intermediate stages of a medical decision-making process (e.g., generating hypotheses or gathering data), instead of focusing only on the final decision. Therefore, we build SepsisLab based on a state-of-the-art AI algorithm and extend it to predict the future projection of sepsis development, visualize the prediction uncertainty, and propose actionable suggestions (i.e., which additional laboratory tests can be collected) to reduce such uncertainty. Through heuristic evaluation with six clinicians using our prototype system, we demonstrate that SepsisLab enables a promising human-AI collaboration paradigm for the future of AI-assisted sepsis diagnosis and other high-stakes medical decision making.

Guangxuan Xu, Paulina Toro Isaza, Moshi Li et al.

To understand a narrative, it is essential to comprehend the temporal event flows, especially those associated with main characters; however, this can be challenging with lengthy and unstructured narrative texts. To address this, we introduce NECE, an open-access, document-level toolkit that automatically extracts and aligns narrative events in the temporal order of their occurrence. Through extensive evaluations, we show the high quality of the NECE toolkit and demonstrates its downstream application in analyzing narrative bias regarding gender. We also openly discuss the shortcomings of the current approach, and potential of leveraging generative models in future works. Lastly the NECE toolkit includes both a Python library and a user-friendly web interface, which offer equal access to professionals and layman audience alike, to visualize event chain, obtain narrative flows, or study narrative bias.

Yuxuan Lu, Jing Huang, Yan Han et al.

Recent research shows that LLM Agents can generate ``believable'' human behaviors via prompt-only methods, and such agents have been increasingly adopted in downstream applications. However, existing evaluation of these agents only focuses on qualitative believability (whether human raters think they are accurate), leaving open questions of whether LLM agents can accurately generate step-by-step actions mimicking a particular human's behavior in a multi-turn interaction task. In this work, we take shopping as a case study and present the first large-scale quantitative evaluation of state-of-the-art LLMs' ability to accurately simulate human behavior. Using real-world data from 31,865 online shopping sessions containing 230,965 user actions, our evaluation reveals that prompt-based LLMs (DeepSeek-R1, Llama, Claude) achieve only 11.86% accuracy in generating human actions, highlighting a substantial gap in actual behavioral accuracy. Through experiments, we also showcase that strategies as simple as fine-tuning LLMs on real human click-through data augmented with synthesized reasoning traces can greatly enhance models' performance. The fine-tuned Qwen2.5-7B achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing substantial improvements of 5.4% and 13.85% over prompt-only baselines. This work establishes the first rigorous benchmark for human behavior simulation and provides actionable insights for developing more accurate LLM agents for future downstream applications.

Yuxuan Lu, Bingsheng Yao, Shao Zhang et al.

Large Language Models (LLMs) have demonstrated considerable advances, and several claims have been made about their exceeding human performance. However, in real-world tasks, domain knowledge is often required. Low-resource learning methods like Active Learning (AL) have been proposed to tackle the cost of domain expert annotation, raising this question: Can LLMs surpass compact models trained with expert annotations in domain-specific tasks? In this work, we conduct an empirical experiment on four datasets from three different domains comparing SOTA LLMs with small models trained on expert annotations with AL. We found that small models can outperform GPT-3.5 with a few hundreds of labeled data, and they achieve higher or similar performance with GPT-4 despite that they are hundreds time smaller. Based on these findings, we posit that LLM predictions can be used as a warmup method in real-world applications and human experts remain indispensable in tasks involving data annotation driven by domain-specific knowledge.

Ziqi Yang, Xuhai Xu, Bingsheng Yao et al.

Despite the plethora of telehealth applications to assist home-based older adults and healthcare providers, basic messaging and phone calls are still the most common communication methods, which suffer from limited availability, information loss, and process inefficiencies. One promising solution to facilitate patient-provider communication is to leverage large language models (LLMs) with their powerful natural conversation and summarization capability. However, there is a limited understanding of LLMs' role during the communication. We first conducted two interview studies with both older adults (N=10) and healthcare providers (N=9) to understand their needs and opportunities for LLMs in patient-provider asynchronous communication. Based on the insights, we built an LLM-powered communication system, Talk2Care, and designed interactive components for both groups: (1) For older adults, we leveraged the convenience and accessibility of voice assistants (VAs) and built an LLM-powered VA interface for effective information collection. (2) For health providers, we built an LLM-based dashboard to summarize and present important health information based on older adults' conversations with the VA. We further conducted two user studies with older adults and providers to evaluate the usability of the system. The results showed that Talk2Care could facilitate the communication process, enrich the health information collected from older adults, and considerably save providers' efforts and time. We envision our work as an initial exploration of LLMs' capability in the intersection of healthcare and interpersonal communication.

Bingsheng Yao, Yao Du, Yue Fu et al.

Advanced AI technologies are increasingly integrated into clinical domains to advance patient care. The design and development of clinical AI technologies necessitate seamless collaboration between clinical and technical experts. However, such interdisciplinary teams are often unsuccessful, with a lack of systematic analysis of collaboration barriers and coping strategies. This work examines two clinical AI collaborations in the context of speech-language pathology via semi-structured interviews with six clinical and seven technical experts. Using Activity Theory (AT) as our analytical lens, we examine persistent knowledge gaps and collaboration tensions across clinical and technical workflows, and show how clinical data can function as boundary objects while interdisciplinary collaborators may act as knowledge brokers to help address these challenges. Our findings contribute to CSCW research on interdisciplinary teams' data work by showing how shared clinical data, boundary objects, and broker roles shape coordination in early-stage clinical AI collaboration, and by providing insights into best practices for future collaboration.

Zhiping Zhang, Chenxinran Shen, Bingsheng Yao et al.

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.

Jiessie Tie, Bingsheng Yao, Tianshi Li et al.

Software engineers are increasingly incorporating AI assistants into their workflows to enhance productivity and alleviate cognitive load. However, experiences with large language models (LLMs) such as ChatGPT vary widely. While some engineers find them useful, others deem them counterproductive due to inaccuracies in their responses. Researchers have also observed that ChatGPT often provides incorrect information. Given these limitations, it is crucial to determine how to effectively integrate LLMs into software engineering (SE) workflow. Analyzing data from 26 participants in a complex web development task, we identified nine failure types categorized into incorrect or incomplete responses, cognitive overload, and context loss. Users attempted to mitigate these issues through scaffolding, prompt clarification, and debugging. However, 17 participants ultimately chose to abandon ChatGPT due to persistent failures. Our quantitative analysis revealed that unhelpful responses increased the likelihood of abandonment by a factor of 11, while each additional prompt reduced abandonment probability by 17%. This study advances the understanding of human-AI interaction in SE tasks and outlines directions for future research and tooling support.

Ronald Cardenas, Bingsheng Yao, Dakuo Wang et al.

Science journalism refers to the task of reporting technical findings of a scientific paper as a less technical news article to the general public audience. We aim to design an automated system to support this real-world task (i.e., automatic science journalism) by 1) introducing a newly-constructed and real-world dataset (SciTechNews), with tuples of a publicly-available scientific paper, its corresponding news article, and an expert-written short summary snippet; 2) proposing a novel technical framework that integrates a paper's discourse structure with its metadata to guide generation; and, 3) demonstrating with extensive automatic and human experiments that our framework outperforms other baseline methods (e.g. Alpaca and ChatGPT) in elaborating a content plan meaningful for the target audience, simplifying the information selected, and producing a coherent final report in a layman's style.

Maya Kruse, Shiyue Hu, Nicholas Derby et al.

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.

Jiahao Xu, Changchang Yin, Odysseas Chatzipanagiotou et al.

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.

Xiangyang Mou, Chenghao Yang, Mo Yu et al.

Recent advancements in open-domain question answering (ODQA), i.e., finding answers from large open-domain corpus like Wikipedia, have led to human-level performance on many datasets. However, progress in QA over book stories (Book QA) lags behind despite its similar task formulation to ODQA. This work provides a comprehensive and quantitative analysis about the difficulty of Book QA: (1) We benchmark the research on the NarrativeQA dataset with extensive experiments with cutting-edge ODQA techniques. This quantifies the challenges Book QA poses, as well as advances the published state-of-the-art with a $\sim$7\% absolute improvement on Rouge-L. (2) We further analyze the detailed challenges in Book QA through human studies.\footnote{\url{https://github.com/gorov/BookQA}.} Our findings indicate that the event-centric questions dominate this task, which exemplifies the inability of existing QA models to handle event-oriented scenarios.

Zhihan Jiang, Mengyuan Millie Wu, Ruishi Zou et al.

Individuals frequently form deep attachments to physical objects (e.g., plush toys) that usually cannot sense or respond to their emotions. While AI companions offer responsiveness and personalization, they exist independently of these physical objects and lack an ongoing connection to them. To bridge this gap, we conducted a formative study (N=9) to explore how digital agents could inherit and extend the emotional bond, deriving four design principles (Faithful Identity, Calibrated Agency, Ambient Presence, and Reciprocal Memory). We then present the Dual-Embodiment Companion Framework, instantiated as Deco, a mobile system integrating multimodal Large Language Models (LLMs) and Augmented Reality to create synchronized digital embodiments of users' physical companions. A within-subjects study (N=25) showed Deco significantly outperformed a personalized LLM-empowered digital companion baseline on perceived companionship, emotional bond, and design-principle scales (all p<0.01). A seven-day field deployment (N=17) showed sustained engagement, subjective well-being improvement (p=.040), and three key relational patterns: digital activities retroactively vitalized physical objects, bond deepening was driven by emotional engagement depth rather than interaction frequency, and users sustained bonds while actively navigating digital companions' AI nature. This work highlights a promising alternative for designing digital companions: moving from creating new relationships to dual embodiment, where digital agents seamlessly extend the emotional history of physical objects.

Tianshi Li, Sauvik Das, Hao-Ping Lee et al. · cmu

The emergence of large language models (LLMs), and their increased use in user-facing systems, has led to substantial privacy concerns. To date, research on these privacy concerns has been model-centered: exploring how LLMs lead to privacy risks like memorization, or can be used to infer personal characteristics about people from their content. We argue that there is a need for more research focusing on the human aspect of these privacy issues: e.g., research on how design paradigms for LLMs affect users' disclosure behaviors, users' mental models and preferences for privacy controls, and the design of tools, systems, and artifacts that empower end-users to reclaim ownership over their personal data. To build usable, efficient, and privacy-friendly systems powered by these models with imperfect privacy properties, our goal is to initiate discussions to outline an agenda for conducting human-centered research on privacy issues in LLM-powered systems. This Special Interest Group (SIG) aims to bring together researchers with backgrounds in usable security and privacy, human-AI collaboration, NLP, or any other related domains to share their perspectives and experiences on this problem, to help our community establish a collective understanding of the challenges, research opportunities, research methods, and strategies to collaborate with researchers outside of HCI.

Yuxuan Lu, Bingsheng Yao, Hansu Gu et al.

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.

Chaoran Chen, Bingsheng Yao, Ruishi Zou et al.

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.

Dakuo Wang, Ting-Yao Hsu, Yuxuan Lu et al.

A/B testing experiment is a widely adopted method for evaluating UI/UX design decisions in modern web applications. Yet, traditional A/B testing remains constrained by its dependence on the large-scale and live traffic of human participants, and the long time of waiting for the testing result. Through formative interviews with six experienced industry practitioners, we identified critical bottlenecks in current A/B testing workflows. In response, we present AgentA/B, a novel system that leverages Large Language Model-based autonomous agents (LLM Agents) to automatically simulate user interaction behaviors with real webpages. AgentA/B enables scalable deployment of LLM agents with diverse personas, each capable of navigating the dynamic webpage and interactively executing multi-step interactions like search, clicking, filtering, and purchasing. In a demonstrative controlled experiment, we employ AgentA/B to simulate a between-subject A/B testing with 1,000 LLM agents Amazon.com, and compare agent behaviors with real human shopping behaviors at a scale. Our findings suggest AgentA/B can emulate human-like behavior patterns.

Jiaju Chen, Yuxuan Lu, Xiaojie Wang et al.

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.

Siyi Wu, Julie Y. A. Cachia, Feixue Han et al.

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.

Yuxuan Lu, Bingsheng Yao, Hansu Gu et al.

Usability testing is a fundamental research method that user experience (UX) researchers use to evaluate and iterate their new designs. But what about evaluating and iterating the usability testing study design itself? Recent advances in Large Language Model-simulated Agent (LLM Agent) research inspired us to design UXAgent to support UX researchers in evaluating and iterating their study design before they conduct the real human-subject study. Our system features a Persona Generator module, an LLM Agent module, and a Universal Browser Connector module to automatically generate thousands of simulated users and to interactively test the target website. The system also provides a Result Viewer Interface so that the UX researchers can easily review and analyze the generated qualitative (e.g., agents' post-study surveys) and quantitative data (e.g., agents' interaction logs), or even interview agents directly. Through a heuristic evaluation with 16 UX researchers, participants praised the innovation of our system but also expressed concerns about the future of LLM Agent usage in UX studies.

Yuxuan Lu, Jing Huang, Yan Han et al.

Recent research shows that LLM Agents can generate ``believable'' human behaviors via prompt-only methods, and such agents have been increasingly adopted in downstream applications. However, existing evaluation of these agents only focuses on qualitative believability (whether human raters think they are accurate), leaving open questions of whether LLM agents can accurately generate step-by-step actions mimicking a particular human's behavior in a multi-turn interaction task. In this work, we take shopping as a case study and present the first large-scale quantitative evaluation of state-of-the-art LLMs' ability to accurately simulate human behavior. Using real-world data from 31,865 online shopping sessions containing 230,965 user actions, our evaluation reveals that prompt-based LLMs (DeepSeek-R1, Llama, Claude) achieve only 11.86% accuracy in generating human actions, highlighting a substantial gap in actual behavioral accuracy. Through experiments, we also showcase that strategies as simple as fine-tuning LLMs on real human click-through data augmented with synthesized reasoning traces can greatly enhance models' performance. The fine-tuned Qwen2.5-7B achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing substantial improvements of 5.4% and 13.85% over prompt-only baselines. This work establishes the first rigorous benchmark for human behavior simulation and provides actionable insights for developing more accurate LLM agents for future downstream applications.

Jingyu Tang, Chaoran Chen, Jiawen Li et al.

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.

Lu Sun, Shihan Fu, Bingsheng Yao et al.

Agentic AI is emerging, capable of executing tasks through natural language, such as Copilot for coding or Amazon Rufus for shopping. Evaluating these systems is challenging, as their rapid evolution outpaces traditional human evaluation. Researchers have proposed LLM Agents to simulate participants as digital twins, but it remains unclear to what extent a digital twin can represent a specific customer in multi-turn interaction with an agentic AI system. In this paper, we recruited 40 human participants to shop with Amazon Rufus, collected their personas, interaction traces, and UX feedback, and then created digital twins to repeat the task. Pairwise comparison of human and digital-twin traces shows that while agents often explored more diverse choices, their action patterns aligned with humans and yielded similar design feedback. This study is the first to quantify how closely LLM agents can mirror human multi-turn interaction with an agentic AI system, highlighting their potential for scalable evaluation.

Ziqi Yang, Yuxuan Lu, Jennifer Bagdasarian et al.

Cancer surgery is a key treatment for gastrointestinal (GI) cancers, a group of cancers that account for more than 35% of cancer-related deaths worldwide, but postoperative complications are unpredictable and can be life-threatening. In this paper, we investigate how recent advancements in large language models (LLMs) can benefit remote patient monitoring (RPM) systems through clinical integration by designing RECOVER, an LLM-powered RPM system for postoperative GI cancer care. To closely engage stakeholders in the design process, we first conducted seven participatory design sessions with five clinical staff and interviewed five cancer patients to derive six major design strategies for integrating clinical guidelines and information needs into LLM-based RPM systems. We then designed and implemented RECOVER, which features an LLM-powered conversational agent for cancer patients and an interactive dashboard for clinical staff to enable efficient postoperative RPM. Finally, we used RECOVER as a pilot system to assess the implementation of our design strategies with four clinical staff and five patients, providing design implications by identifying crucial design elements, offering insights on responsible AI, and outlining opportunities for future LLM-powered RPM systems.

Changchang Yin, Shihan Fu, Bingsheng Yao et al.

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.

Jiachen Li, Xiwen Li, Justin Steinberg et al.

Passive tracking methods, such as phone and wearable sensing, have become dominant in monitoring human behaviors in modern ubiquitous computing studies. While there have been significant advances in machine-learning approaches to translate periods of raw sensor data to model momentary behaviors, (e.g., physical activity recognition), there still remains a significant gap in the translation of these sensing streams into meaningful, high-level, context-aware insights that are required for various applications (e.g., summarizing an individual's daily routine). To bridge this gap, experts often need to employ a context-driven sensemaking process in real-world studies to derive insights. This process often requires manual effort and can be challenging even for experienced researchers due to the complexity of human behaviors. We conducted three rounds of user studies with 21 experts to explore solutions to address challenges with sensemaking. We follow a human-centered design process to identify needs and design, iterate, build, and evaluate Vital Insight (VI), a novel, LLM-assisted, prototype system to enable human-in-the-loop inference (sensemaking) and visualizations of multi-modal passive sensing data from smartphones and wearables. Using the prototype as a technology probe, we observe experts' interactions with it and develop an expert sensemaking model that explains how experts move between direct data representations and AI-supported inferences to explore, question, and validate insights. Through this iterative process, we also synthesize and discuss a list of design implications for the design of future AI-augmented visualization systems to better assist experts' sensemaking processes in multi-modal health sensing data.

Menglin Zhao, Zhuorui Yong, Ruijia Guan et al.

Serious illness conversations (SICs), discussions between clinical care teams and patients with serious, life-limiting illnesses about their values, goals, and care preferences, are critical for patient-centered care. Without these conversations, patients often receive aggressive interventions that may not align with their goals. Clinical care teams face significant barriers when conducting serious illness conversations with older adult patients in Emergency Department (ED) settings, where most older adult patients lack documented treatment goals. To understand current practices and identify AI support opportunities, we conducted interviews with two domain experts and nine ED clinical care team members. Through thematic analysis, we characterized a four-phase serious illness conversation workflow (identification, preparation, conduction, documentation) and identified key needs and challenges at each stage. Clinical care teams struggle with fragmented EHR data access, time constraints, emotional preparation demands, and documentation burdens. While participants expressed interest in AI tools for information synthesis, conversational support, and automated documentation, they emphasized preserving human connection and clinical autonomy. We present design guidelines for AI tools supporting SIC workflows that fit within existing clinical practices. This work contributes empirical understanding of ED-based serious illness conversations and provides design considerations for AI in high-stakes clinical environments.

Shihan Fu, Bingsheng Yao, Smit Desai et al.

Older adult patients constitute a rapidly growing subgroup of Intensive Care Unit (ICU) patients. In these situations, their family caregivers are expected to represent the unconscious patients to access and interpret patients' medical information. However, caregivers currently have to rely on overloaded clinicians for information updates and typically lack the health literacy to understand complex medical information. Our project aims to explore the information needs of caregivers of ICU older adult patients, from which we can propose design opportunities to guide future AI systems. The project begins with formative interviews with 11 caregivers to identify their challenges in accessing and interpreting medical information; From these findings, we then synthesize design requirements and propose an AI system prototype to cope with caregivers' challenges. The system prototype has two key features: a timeline visualization to show the AI extracted and summarized older adult patients' key medical events; and an LLM-based chatbot to provide context-aware informational support. We conclude our paper by reporting on the follow-up user evaluation of the system and discussing future AI-based systems for ICU caregivers of older adults.

Bingsheng Yao, Bo Sun, Yuanzhe Dong et al.

The emerging large language model role-playing agents (LLM RPAs) aim to simulate individual human behaviors, but the persona fidelity is often undermined by manually-created profiles (e.g., cherry-picked information and personality characteristics) without validating the alignment with the target individuals. To address this limitation, our work introduces the Dynamic Persona Refinement Framework (DPRF). DPRF aims to optimize the alignment of LLM RPAs' behaviors with those of target individuals by iteratively identifying the cognitive divergence, either through free-form or theory-grounded, structured analysis, between generated behaviors and human ground truth, and refining the persona profile to mitigate these divergences. We evaluate DPRF with five LLMs on four diverse behavior-prediction scenarios: formal debates, social media posts with mental health issues, public interviews, and movie reviews. DPRF can consistently improve behavioral alignment considerably over baseline personas and generalizes across models and scenarios. Our work provides a robust methodology for creating high-fidelity persona profiles and enhancing the validity of downstream applications, such as user simulation, social studies, and personalized AI.

Bingsheng Yao, Jiaju Chen, Chaoran Chen et al.

Intelligent systems have traditionally been designed as tools rather than collaborators, often lacking critical characteristics that collaboration partnerships require. Recent advances in large language model (LLM) agents open new opportunities for human-LLM-agent collaboration by enabling natural communication and various social and cognitive behaviors. Yet it remains unclear whether principles of computer-mediated collaboration established in HCI and CSCW persist, change, or fail when humans collaborate with LLM agents. To support systematic investigations of these questions, we introduce an open and configurable research platform for HCI researchers. The platform's modular design allows seamless adaptation of classic CSCW experiments and manipulation of theory-grounded interaction controls. We demonstrate the platform's effectiveness and usability through two case studies: (1) re-implementing the classic human-human-collaboration task Shape Factory as a between-subject human-agent-collaboration experiment with 16 participants, and (2) a participatory cognitive walkthrough with five HCI researchers to refine workflows and interfaces for experiment setup and analysis.

Ying Lei, Yancheng Cao, Will Wang et al.

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.

Bingsheng Yao, Ishan Jindal, Lucian Popa et al.

Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support human annotators mostly focus on the label while neglecting the natural language explanation of a data point. This work proposes a novel AL architecture to support experts' real-world need for label and explanation annotations in low-resource scenarios. Our AL architecture leverages an explanation-generation model to produce explanations guided by human explanations, a prediction model that utilizes generated explanations toward prediction faithfully, and a novel data diversity-based AL sampling strategy that benefits from the explanation annotations. Automated and human evaluations demonstrate the effectiveness of incorporating explanations into AL sampling and the improved human annotation efficiency and trustworthiness with our AL architecture. Additional ablation studies illustrate the potential of our AL architecture for transfer learning, generalizability, and integration with large language models (LLMs). While LLMs exhibit exceptional explanation-generation capabilities for relatively simple tasks, their effectiveness in complex real-world tasks warrants further in-depth study.

Bingsheng Yao, Prithviraj Sen, Lucian Popa et al.

Human-annotated labels and explanations are critical for training explainable NLP models. However, unlike human-annotated labels whose quality is easier to calibrate (e.g., with a majority vote), human-crafted free-form explanations can be quite subjective. Before blindly using them as ground truth to train ML models, a vital question needs to be asked: How do we evaluate a human-annotated explanation's quality? In this paper, we build on the view that the quality of a human-annotated explanation can be measured based on its helpfulness (or impairment) to the ML models' performance for the desired NLP tasks for which the annotations were collected. In comparison to the commonly used Simulatability score, we define a new metric that can take into consideration the helpfulness of an explanation for model performance at both fine-tuning and inference. With the help of a unified dataset format, we evaluated the proposed metric on five datasets (e.g., e-SNLI) against two model architectures (T5 and BART), and the results show that our proposed metric can objectively evaluate the quality of human-annotated explanations, while Simulatability falls short.

Zheng Zhang, Ying Xu, Yanhao Wang et al.

Despite its benefits for children's skill development and parent-child bonding, many parents do not often engage in interactive storytelling by having story-related dialogues with their child due to limited availability or challenges in coming up with appropriate questions. While recent advances made AI generation of questions from stories possible, the fully-automated approach excludes parent involvement, disregards educational goals, and underoptimizes for child engagement. Informed by need-finding interviews and participatory design (PD) results, we developed StoryBuddy, an AI-enabled system for parents to create interactive storytelling experiences. StoryBuddy's design highlighted the need for accommodating dynamic user needs between the desire for parent involvement and parent-child bonding and the goal of minimizing parent intervention when busy. The PD revealed varied assessment and educational goals of parents, which StoryBuddy addressed by supporting configuring question types and tracking child progress. A user study validated StoryBuddy's usability and suggested design insights for future parent-AI collaboration systems.

Bingsheng Yao, Dakuo Wang, Tongshuang Wu et al.

Existing question answering (QA) techniques are created mainly to answer questions asked by humans. But in educational applications, teachers often need to decide what questions they should ask, in order to help students to improve their narrative understanding capabilities. We design an automated question-answer generation (QAG) system for this education scenario: given a story book at the kindergarten to eighth-grade level as input, our system can automatically generate QA pairs that are capable of testing a variety of dimensions of a student's comprehension skills. Our proposed QAG model architecture is demonstrated using a new expert-annotated FairytaleQA dataset, which has 278 child-friendly storybooks with 10,580 QA pairs. Automatic and human evaluations show that our model outperforms state-of-the-art QAG baseline systems. On top of our QAG system, we also start to build an interactive story-telling application for the future real-world deployment in this educational scenario.

Xiangyang Mou, Mo Yu, Bingsheng Yao et al.

A lot of progress has been made to improve question answering (QA) in recent years, but the special problem of QA over narrative book stories has not been explored in-depth. We formulate BookQA as an open-domain QA task given its similar dependency on evidence retrieval. We further investigate how state-of-the-art open-domain QA approaches can help BookQA. Besides achieving state-of-the-art on the NarrativeQA benchmark, our study also reveals the difficulty of evidence retrieval in books with a wealth of experiments and analysis - which necessitates future effort on novel solutions for evidence retrieval in BookQA.

Jaimie Drozdal, Justin Weisz, Dakuo Wang et al.

We explore trust in a relatively new area of data science: Automated Machine Learning (AutoML). In AutoML, AI methods are used to generate and optimize machine learning models by automatically engineering features, selecting models, and optimizing hyperparameters. In this paper, we seek to understand what kinds of information influence data scientists' trust in the models produced by AutoML? We operationalize trust as a willingness to deploy a model produced using automated methods. We report results from three studies -- qualitative interviews, a controlled experiment, and a card-sorting task -- to understand the information needs of data scientists for establishing trust in AutoML systems. We find that including transparency features in an AutoML tool increased user trust and understandability in the tool; and out of all proposed features, model performance metrics and visualizations are the most important information to data scientists when establishing their trust with an AutoML tool.