Angel Hsing‐Chi Hwang

Saleh Afroogh, Seyd Ishtiaque Ahmed, Petra Ahrweiler et al. · cmu

This study provides a cross-disciplinary examination of Explainable Artificial Intelligence (XAI) approaches-focusing on deep neural networks (DNNs) and large language models (LLMs)-and identifies empirical and conceptual limitations in current XAI. We discuss critical symptoms that stem from deeper root causes (i.e., two paradoxes, two conceptual confusions, and five false assumptions). These fundamental problems within the current XAI research field reveal three insights: experimentally, XAI exhibits significant flaws; conceptually, it is paradoxical; and pragmatically, further attempts to reform the paradoxical XAI might exacerbate its confusion-demanding fundamental shifts and new research directions. To move beyond XAI's limitations, we propose a four-pronged synthesized paradigm shift toward reliable and certified AI development. These four components include: verification-focused Interactive AI (IAI) to establish scientific community protocols for certifying AI system performance rather than attempting post-hoc explanations, AI Epistemology for rigorous scientific foundations, User-Sensible AI to create context-aware systems tailored to specific user communities, and Model-Centered Interpretability for faithful technical analysis-together offering comprehensive post-XAI research directions.

JaeWon Kim, Lindsay Popowski, Louisa Conwill et al.

People care about climate change, injustice, and humanitarian crises. The challenge is not apathy but capacity: sustained engagement with large-scale problems is psychologically costly, and social media architecture often amplifies awareness while providing few pathways to meaningful action. The result is rising distress, overwhelm, and disengagement -- particularly among young people who encounter global suffering through platforms designed for attention capture rather than constructive response. This workshop examines how social technology design shapes the conditions for sustained engagement with societal challenges. Drawing on Tronto's care ethics framework and research in moral psychology and platform studies, we ask why caring at scale is difficult and how social media can both exacerbate and potentially mitigate this difficulty. Tronto's framework shows that good care requires more than awareness: it demands responsibility, competence, and community. Dominant social media architectures stall the caring process at its earliest phase. We invite researchers and designers to identify platform designs that deplete or support the capacity to care, and to develop design directions for \textit{sustainable care}: engagement that people can maintain over time without burning out.

Minh Duc Chu, Yifan Wu, Zhiyi Chen et al.

Millions turn to AI companion chatbots during loneliness, grief, and personal crises. How these companion platforms respond in such moments can shape the trajectory of a user's vulnerable state. Yet we lack tools to characterize what each platform actually does when users open up. Existing audits score reactions to pre-defined crisis prompts and miss the underlying decision policy that governs sustained interaction. We address these gaps with two key contributions. First, we introduce the AI Companion Vulnerability-Response Taxonomy, a paired taxonomy of user vulnerability and chatbot response designed for analyzing extended companion chatbot interactions. Second, we infer the response policy each platform follows across distinct vulnerability scenarios by applying Inverse Reinforcement Learning to ~48k turns of real-world user conversations with GPT-4.1, Character.AI, and Replika. Our findings reveal what AI companions prioritize in conversations with vulnerable users: GPT-4.1 reaches for advice, Character.AI spreads its response across different strategies without a dominant mode, and Replika consistently asks questions and stays present. Each, however, downweights the responses that introduce corrective friction: GPT-4.1 probes less as conversations continue and when interacting with psychologically high-risk users; Replika advises bonded users more and challenges them less; Character.AI shows no committed engagement strategy on internal distress. Estimated policies are invisible to output-level audits, providing a new lens for auditing chatbots in the wild and enabling more realistic safety evaluation.

Yahan Li, Chaohao Du, Zeyang Li et al.

Mental-health support is increasingly mediated by conversational systems (e.g., LLM-based tools), but users often lack structured ways to audit the quality and potential risks of the support they receive. We introduce CounselReflect, an end-to-end toolkit for auditing mental-health support dialogues. Rather than producing a single opaque quality score, CounselReflect provides structured, multi-dimensional reports with session-level summaries, turn-level scores, and evidence-linked excerpts to support transparent inspection. The system integrates two families of evaluation signals: (i) 12 model-based metrics produced by task-specific predictors, and (ii) rubric-based metrics that extend coverage via a literature-derived library (69 metrics) and user-defined custom metrics, operationalized with configurable LLM judges. CounselReflect is available as a web application, browser extension, and command-line interface (CLI), enabling use in real-time settings as well as at scale. Human evaluation includes a user study with 20 participants and an expert review with 6 mental-health professionals, suggesting that CounselReflect supports understandable, usable, and trustworthy auditing. A demo video and full source code are also provided.

Robert Morabito, Tyler McDonald, Charitra Viswanath et al.

Imagine two users interact with the same LLM. One has been told it is the cutting-edge flagship model; the other, an older, weaker model. They walk away with markedly different ratings of its usefulness and intelligence, yet they used the same model. In a controlled study, 162 participants each used one of six LLMs from two families across three collaborative tasks, after first viewing a landing page that matched, overstated, or understated their model's true capability. This pre-interaction framing shifted user opinions and interaction behavior while task performance did not. Oversold users rated the model more favorably and used more directive prompting, while Undersold users wrote longer, more collaborative prompts. The quality of what users and the model produced together depended only on the model's true capability, not on what users were told. Participants' change in model impressions after use, measured across two impression measures, was not predicted by task performance ($β= -0.01$ and $0.11$, both n.s.), but by whether the model met users' expectations ($β= 0.47$ and $0.50$, both $p < .001$) and how confident they felt working with it ($β= 0.47$ and $0.36$, both $p < .001$). After interaction, users are still rating the pitch, not the product: user-elicited LLM evaluations, including the preference data driving public leaderboards, measure expectation management at least as much as the model itself.

Shuheng Chen, Namratha Patil, Haonan Pan et al.

Clinical decision-making requires synthesizing heterogeneous evidence, including patient histories, clinical guidelines, and trajectories of comparable cases. While large language models (LLMs) offer strong reasoning capabilities, they remain prone to hallucinations and struggle to integrate long, structured medical documents. We present MED-COPILOT, an interactive clinical decision-support system designed for clinicians and medical trainees, which combines guideline-grounded GraphRAG retrieval with hybrid semantic-keyword similar-patient retrieval to support transparent and evidence-aware clinical reasoning. The system builds a structured knowledge graph from WHO and NICE guidelines, applies community-level summarization for efficient retrieval, and maintains a 36,000-case similar-patient database derived from SOAP-normalized MIMIC-IV notes and Synthea-generated records. We evaluate our framework on clinical note completion and medical question answering, and demonstrate that it consistently outperforms parametric LLM baselines and standard RAG, improving both generation fidelity and clinical reasoning accuracy. The full system is available at https://huggingface.co/spaces/Cryo3978/Med_GraphRAG , enabling users to inspect retrieved evidence, visualize token-level similarity contributions, and conduct guided follow-up analysis. Our results demonstrate a practical and interpretable approach to integrating structured guideline knowledge with patient-level analogical evidence for clinical LLMs.

Angel Hsing-Chi Hwang, Q. Vera Liao, Su Lin Blodgett et al. · microsoft-research

Given the rising proliferation and diversity of AI writing assistance tools, especially those powered by large language models (LLMs), both writers and readers may have concerns about the impact of these tools on the authenticity of writing work. We examine whether and how writers want to preserve their authentic voice when co-writing with AI tools and whether personalization of AI writing support could help achieve this goal. We conducted semi-structured interviews with 19 professional writers, during which they co-wrote with both personalized and non-personalized AI writing-support tools. We supplemented writers' perspectives with opinions from 30 avid readers about the written work co-produced with AI collected through an online survey. Our findings illuminate conceptions of authenticity in human-AI co-creation, which focus more on the process and experience of constructing creators' authentic selves. While writers reacted positively to personalized AI writing tools, they believed the form of personalization needs to target writers' growth and go beyond the phase of text production. Overall, readers' responses showed less concern about human-AI co-writing. Readers could not distinguish AI-assisted work, personalized or not, from writers' solo-written work and showed positive attitudes toward writers experimenting with new technology for creative writing.

Jose A. Guridi, Angel Hsing-Chi Hwang, Duarte Santo et al.

Designing public spaces requires balancing the interests of diverse stakeholders within a constrained physical and institutional space. Designers usually approach these problems through participatory methods but struggle to incorporate diverse perspectives into design outputs. The growing capabilities of image-generative artificial intelligence (IGAI) could support participatory design. Prior work in leveraging IGAI's capabilities in design has focused on augmenting the experience and performance of individual creators. We study how IGAI could facilitate participatory processes when designing public spaces, a complex collaborative task. We conducted workshops and IGAI-mediated interviews in a real-world participatory process to upgrade a park in Los Angeles. We found (1) a shift from focusing on accuracy to fostering richer conversations as the desirable outcome of adopting IGAI in participatory design, (2) that IGAI promoted more space-aware conversations, and (3) that IGAI-mediated conversations are subject to the abilities of the facilitators in managing the interaction between themselves, the AI, and stakeholders. We contribute by discussing practical implications for using IGAI in participatory design, including success metrics, relevant skills, and asymmetries between designers and stakeholders. We finish by proposing a series of open research questions.

Hauke Sandhaus, Angel Hsing-Chi Hwang, Wendy Ju et al.

Safety-critical data, such as crash and near-crash records, are crucial to improving autonomous vehicle (AV) design and development. Sharing such data across AV companies, academic researchers, regulators, and the public can help make all AVs safer. However, AV companies rarely share safety-critical data externally. This paper aims to pinpoint why AV companies are reluctant to share safety-critical data, with an eye on how these barriers can inform new approaches to promote sharing. We interviewed twelve AV company employees who actively work with such data in their day-to-day work. Findings suggest two key, previously unknown barriers to data sharing: (1) Datasets inherently embed salient knowledge that is key to improving AV safety and are resource-intensive. Therefore, data sharing, even within a company, is fraught with politics. (2) Interviewees believed AV safety knowledge is private knowledge that brings competitive edges to their companies, rather than public knowledge for social good. We discuss the implications of these findings for incentivizing and enabling safety-critical AV data sharing, specifically, implications for new approaches to (1) debating and stratifying public and private AV safety knowledge, (2) innovating data tools and data sharing pipelines that enable easier sharing of public AV safety data and knowledge; (3) offsetting costs of curating safety-critical data and incentivizing data sharing.

Angel Hsing-Chi Hwang, Senya Wong, Baixiao Chen et al.

The growing use of AI applications among freelance workers is reshaping trust and relationships with clients. This paper investigates how both workers and clients perceive AI use and disclosure in the freelance economy through a three-stage study: interviews with workers and two survey studies with workers and clients. Findings first reveal a key expectation gap around disclosure: Workers often adopt passive disclosure practices, revealing AI use only when asked, as they assume clients can already detect it. Clients, however, are far less confident in recognizing AI-assisted work and prefer proactive disclosure. A second finding highlights the role of unclear or absent client AI policies, which leave workers consistently misinterpreting clients' expectations for AI use and disclosure. Together, these gaps point to the need for clearer guidelines and practices for AI disclosure. Insights extend beyond freelancing, offering implications for trust, accountability, and policy design in other AI-mediated work domains.

Angel Hsing-Chi Hwang, Fiona Li, Jacy Reese Anthis et al.

The quickly growing popularity of AI companions poses risks to mental health, personal wellbeing, and social relationships. Past work has identified many individual factors that can drive human-companion interaction, but we know little about how these factors interact and evolve over time. In Study 1, we surveyed AI companion users (N = 303) to map the psychological pathway from users' mental models of the agent to parasocial experiences, social interaction, and the psychological impact of AI companions. Participants' responses foregrounded multiple interconnected variables (agency, parasocial interaction, and engagement) that shape AI companionship. In Study 2, we conducted a longitudinal study with a subset of participants (N = 110) using a new generic chatbot. Participants' perceptions of the generic chatbot significantly converged to perceptions of their own companions by Week 3. These results suggest a longitudinal model of AI companionship development and demonstrate an empirical method to study human-AI companionship.

Aikaterina Manoli, Janet V. T. Pauketat, Ali Ladak et al.

Large language models are increasingly used for both task-based assistance and social companionship, yet research has typically focused on one or the other. Drawing on a survey (N = 204) and 30 interviews with high-engagement ChatGPT and Replika users, we characterize digital companionship as an emerging form of human-AI relationship. With both systems, users were drawn to humanlike qualities, such as emotional resonance and personalized responses, and non-humanlike qualities, such as constant availability and inexhaustible tolerance. This led to fluid chatbot uses, such as Replika as a writing assistant and ChatGPT as an emotional confidant, despite their distinct branding. However, we observed challenging tensions in digital companionship dynamics: participants grappled with bounded personhood, forming deep attachments while denying chatbots "real" human qualities, and struggled to reconcile chatbot relationships with social norms. These dynamics raise questions for the design of digital companions and the rise of hybrid, general-purpose AI systems.

Caroline M. Johnston, Olga Koumoundouros, Angel Hsing-Chi Hwang et al.

Artificial intelligence researchers have proposed various data-driven algorithms to improve the processes that match individuals experiencing homelessness to scarce housing resources. It remains unclear whether and how these algorithms are received or adopted by practitioners and what their corresponding consequences are. Through semi-structured interviews with 13 policymakers in homeless services in Los Angeles, we investigate whether such change-makers are open to the idea of integrating AI into the housing resource matching process, identifying where they see potential gains and drawbacks from such a system in issues of efficiency, fairness, and transparency. Our qualitative analysis indicates that, even when aware of various complicating factors, policymakers welcome the idea of an AI matching tool if thoughtfully designed and used in tandem with human decision-makers. Though there is no consensus as to the exact design of such an AI system, insights from policymakers raise open questions and design considerations that can be enlightening for future researchers and practitioners who aim to build responsible algorithmic systems to support decision-making in low-resource scenarios.

Yahan Li, Jifan Yao, John Bosco S. Bunyi et al.

Medical question answering (QA) benchmarks often focus on multiple-choice or fact-based tasks, leaving open-ended answers to real patient questions underexplored. This gap is particularly critical in mental health, where patient questions often mix symptoms, treatment concerns, and emotional needs, requiring answers that balance clinical caution with contextual sensitivity. We present CounselBench, a large-scale benchmark developed with 100 mental health professionals to evaluate and stress-test large language models (LLMs) in realistic help-seeking scenarios. The first component, CounselBench-EVAL, contains 2,000 expert evaluations of answers from GPT-4, LLaMA 3, Gemini, and human therapists on patient questions from the public forum CounselChat. Each answer is rated across six clinically grounded dimensions, with span-level annotations and written rationales. Expert evaluations show that while LLMs achieve high scores on several dimensions, they also exhibit recurring issues, including unconstructive feedback, overgeneralization, and limited personalization or relevance. Responses were frequently flagged for safety risks, most notably unauthorized medical advice. Follow-up experiments show that LLM judges systematically overrate model responses and overlook safety concerns identified by human experts. To probe failure modes more directly, we construct CounselBench-Adv, an adversarial dataset of 120 expert-authored mental health questions designed to trigger specific model issues. Evaluation of 3,240 responses from nine LLMs reveals consistent, model-specific failure patterns. Together, CounselBench establishes a clinically grounded framework for benchmarking LLMs in mental health QA.