Papers

We need studies on conversational AI (CAI) at scale to understand human behavior and shape CAI design. However, fragmented reporting of systems and study configurations hinders replication, extension, and knowledge accumulation. We present Gricea, an open-science platform representing studies as configurable, deployable research artifacts that researchers can run, inspect, share, and reuse. Informed by a formative analysis of prior CAI research, Gricea couples study procedures, participant-facing systems, and conversational task behavior in. In a replication study using Gricea, we replicated configurations 93% of eligible CUI 2026 papers; while also flagging missing information in 96% of papers that hinder faithful replication — further motivating Gricea's need. In a user study, researchers and practitioners from diverse backgrounds successfully constructed runnable studies addressing various open-ended research questions. Together, these findings demonstrate Gricea's support for constructing, reproducing, and extending CAI studies through shared research artifacts, enabling cumulative knowledge building through open science.

The growing elderly population gives rise to an urgent need for intelligent support systems, particularly for individuals with Mild Cognitive Impairment (MCI). This paper presents PV-Care, a proactive AI-driven assistance scheme that integrates wearable electroencephalogram (EEG) sensing with visual environmental perception to provide real-time, context-aware voice assistance for MCI users. Unlike traditional assistant systems that passively wait for user commands, PV-Care actively initiates helpful interactions based on the user's detected brain states, including Learning, Memory Recall, and Resting, using a novel deep neural architecture named Spatial and Frequency Refinement Network (SFR-Net). By combining EEG-based cognitive-state recognition with AI-based visual analysis, PV-Care generates structured "4W-UT" prompts to guide the output of large language models (LLMs). Simulation results and user studies validate the high accuracy of the proposed SFR-Net and the effectiveness of PV-Care's context-aware assistance. These results indicate that PV-Care is a feasible and promising solution for MCI caring.

A robot that fails at a task faces the first decision in corrective dialogue: act on its own diagnosis, consult another onboard sensor, or interrupt a person. Choosing well requires knowing how much the robot's sensors reveal about the cause and how reliable the robot's own diagnosis is. We build a simulated benchmark in which every failure's true cause is known, because we injected it, and measure what each sensor reveals, with explicit checks against data leakage. Some failures are diagnosable from camera images; others only from the robot's force data (0.99 from force data, no image method above 0.55). We then test six open vision-language models. Their behavior tracks the surface of the prompt, not the evidence: moving the refusal option from last to first in the answer list collapses refusal rates from 78-100% to 0-6% in three of the six swept model-and-family pairs. Accuracy from frames stays at or below a majority-class baseline under every prompt variant, with or without worked examples, and stated confidence carries no information about correctness. Handing the same models the force data as ten lines of text produces the first above-baseline diagnoses, in four of the six models: much of the failure reflects missing sensor data, not missing ability. We pose the choice as a three-action decision problem, act, consult your own sensors, or ask a human, whose optimal policy follows from measured accuracy. The models do not follow it, and their ask rates ignore a fourfold change in question cost. One question to a human still lifts them from that baseline to roughly the answerer's own reliability (0.70-0.81 when they ask). The decision to ask should be tied to measured accuracy and stated costs, not to the model's confidence.

People increasingly seek mental health support from large language models, yet little is known about their use across years of recurrent panic. We present a three-year analytic autoethnography of the first author's ChatGPT use while living with panic disorder, drawing on conversations, personal records, and accounts from friends or family members and professionals. Narrative analysis traces how my questions shaped ChatGPT's roles and how earlier experiences influenced later responses to symptoms. Familiar explanations could make sensations less frightening, while changed symptoms renewed fears of serious illness. During sudden panic, advice could be difficult to follow, and some replies prompted further checking. Conversations could end while symptoms, checking, or help-seeking continued. We propose trajectory-level safety during and after panic: usable advice (Fit), a stopping point for repeated checking and reassurance seeking (Closure), and useful understanding and human support that remain available over time (Continuity).

As more of everyday life takes place online, digital behavior may provide a potential window into how depressive symptoms are reflected in daily life. Yet digital mental health studies have produced mixed findings. These inconsistencies may partly reflect how digital behavior is measured: self reported use, single device studies, and aggregate screen time can obscure differences across devices, activities, and patterns of engagement. We combined monthly assessments of depressive symptoms with passively recorded mobile and desktop web traces from 1,146 adults in Germany over six months. We examined how general, cognitive-affective, and somatic depressive symptoms are reflected across digital contexts defined by device and activity type. Associations varied markedly across these contexts. On mobile, more severe symptoms were associated with more nighttime activity, greater use of social media, messaging, and entertainment, and fewer but longer sessions. On desktop, associations were fewer and largely involved reduced engagement with news, shopping, and adult content. Mobile associations primarily arose for general and cognitive-affective symptoms, whereas desktop associations were concentrated in somatic symptoms. Our findings suggest that characterizing how depressive symptoms are reflected in digital behavior requires attending to what people do online and where, not only how much screens are used.

Hand tracking offers natural VR interaction but lacks controllers' inherent tactile feedback, while haptic feedback across input methods remains understudied. We conducted a participant study comparing vibration, impulse, and no feedback in hand- and controller-based VR interaction across grasp-, pinch-, and tap-like gestures assessing performance, workload, and preference. A custom glove and controller-mounted device provided both feedback types, aiming for consistency across input modalities. Controllers were faster for grasp and pinch, whereas hand tracking was more accurate for pinch and preferred overall. Haptics had limited performance effects, although impulse reduced grasp accuracy with controllers. Participants preferred vibration and impulse over no haptic feedback, favouring vibration overall. Our findings reveal a more nuanced relationship between haptic feedback, input device, and interaction context than suggested by previous work.

Gratitude technologies support well-being by prompting reflection on what people appreciate. But gratitude does not serve the same purpose in every circumstance: as life situations change, so does what people seek from it, and whether it feels appropriate at all. To understand how technology can adapt to and support such shifts, we conducted retrospective, artifact-elicitation interviews with 17 adults who had practiced gratitude for one to fifteen years. Participants' appraisals of their situations shaped what they needed, yielding six recurring practice patterns, including a boundary where gratitude felt forced. We contribute the Adaptive Gratitude Practice Model, which explains how appraisals shifted even within the same life situation, how participants adapted activities, modalities, and rhythms, lapsed under competing demands or emotional unreadiness, and resumed when gratitude again felt useful. Additionally, we derive design implications for situated support, self-understanding through past records, and relational care with changing life situations.

Blind and low-vision users often face challenges when locating and physically acquiring objects in unfamiliar indoor environments. Existing vision-language-model-based assistants can provide semantic descriptions but may introduce latency, hallucinations, and guidance that is poorly aligned with embodied action. We present Touvigation, a hands-free object acquisition system that combines vision-language understanding with persistent local spatial modeling to provide low-latency, body-relative guidance. Drawing on formative interviews with eight blind and low-vision participants, we design a multi-stage guidance framework that adapts spatial references as users transition from orienting, to walking, to reaching and tactile verification. We evaluated Touvigation with 12 blind and low-vision participants against a multimodal large-language-model assistant and unassisted search. Touvigation achieved 100% task success, compared with 58% for the multimodal assistant and 85% for unassisted search, while reducing completion time and cognitive workload. Our findings demonstrate how persistent spatial grounding and adaptive embodied guidance can improve object acquisition for blind and low-vision users.

Background: Just-in-time adaptive interventions (JITAIs) can use behavioral data to adapt support to changing contexts, but many rely on predefined rules and manual configuration. Objective: We developed a proof-of-concept sleep JITAI using an AI agent to review personal data, evaluate reminders, adapt interventions, and record decisions for human review. Methods: Running in Home Assistant on a configurable schedule, the agent follows a reusable skill file to review 30 days of sleep and behavioral data, including physical activity, smartphone use, and bedtime routines, to identify patterns and create or update automated reminders. Results: Initial runs demonstrated technical feasibility, successfully completing data review and intervention decisions while limiting reminders to three per day and saving decision records. Conclusions: Agentic AI may enable flexible, adaptive sleep JITAIs. The architecture supports future comparison with fixed or rulebased interventions, requires human oversight, and could extend to other health behaviors.

Previous research suggests that the congruency between common VR input devices - such as controllers or hand tracking - and their visual representations (e.g., hand or controller avatars) influences user experience and performance. However, the specific effects of input-avatar combinations remain underexplored. We study the effects of common input devices (hand tracking and controllers) and visual representations (hand and controller avatars) on performance and perceived success in target acquisition tasks. We included both grasping and pinching gestures across 16 combinations of input, avatar, and target size. Results indicate that hand tracking benefits from any form of visual representation - even when mismatched - achieving up to 5.8% greater accuracy compared to having no avatar, likely due to its reliance on visual feedback in the absence of a physical prop. Controllers were generally preferred and offered faster task completion. However, mismatched avatars had a stronger negative effect with controllers, particularly when the virtual gesture did not align with the physical action, leading to a 5.6% drop in accuracy compared to the matched condition - suggesting that inaccurate feedback can be more disruptive than having no avatar feedback at all.

Computational notebooks make problem-solving visible, but typically only one notebook at a time. Meanwhile, in data science platforms like Kaggle, one competition can accumulate hundreds of notebooks. Effective collection-level analysis requires characterizing recurring solution patterns across all notebooks, as well as isolating specific notebooks for closer examination and learning. However, standard notebooks provide no common basis for this. Their workflows are nonlinear, cells declare no intent, and identical code can serve different ends, leaving hundreds of notebooks as separate documents. In this paper, we present Notrix, an interactive visual analytics tool for profiling hundreds of notebooks as one collection. Inspired by a formative study (N = 11), Notrix classifies every cell into one of thirteen machine learning (ML) stages, turning each notebook into a stage sequence, and clusters those sequences by structure rather than by code. To keep the representation constant as the scope narrows from the whole collection to a single cell, Notrix features three coordinated views—Workflow, Structural Matrix, and Detail—that appear at all four levels of granularity. In a within-subject study (N = 17) using two Kaggle collections of over 400 notebooks each, we observed participants answered questions about all notebooks more accurately with Notrix (median 88% vs. 50%) while opening 80% fewer notebooks per minute. Notably, four of the fourteen answered it without opening a single notebook (interaction logs, N = 14). Participants also reported significantly lower mental demand, temporal demand, and stress with Notrix (Holm-Bonferroni adjusted).

Problematic internet use affects a growing share of the population, yet common interventions, e.g., time limits, blocking, forced breaks, are coercive and easily circumvented. We explore a less restrictive alternative: adapting the emotional intensity of visual content. Prior work has shown that optimization can steer an image's affective content, but its per-image optimization cost makes it impractical for real-time deployment. We instead learn a model that predicts this transformation in a single forward pass: a MobileNetV4 backbone with FiLM-based emotion conditioning outputs parameters for differentiable global transformations. This replaces prior iterative optimization (80 s per image) with a single 3.7 ms forward pass. In a user study (N = 54), the model reduced viewer-reported arousal relative to unedited images, comparably to the grayscale well-being filter, while being rated higher in perceived quality. We integrate the model into an Android app that adapts Instagram video in real time, sustaining 60 fps on a Samsung Galaxy S23.

Despite a growing demand for causal evidence about social media, independent researchers remain severely constrained in their ability to conduct experiments directly on online platforms. To cope, multiple methodological workarounds have emerged - from controlled surveys and simulations to client-side overlays and platform partnerships - each requiring distinct trade-offs between desirable experimental properties. The recent emergence of open social media platforms offers a qualitatively different methodological opportunity. Here we propose a design space of social media experimentation and discuss Open Platform Field Experiments (OPFEs). OPFEs represent a distinct class of experimental approaches that enable independent researchers to directly intervene on functional platform components - such as clients, recommendation systems, and moderation services - within live social media environments. Through a comparative analysis of experimental archetypes, we show that OPFEs occupy a previously unexplored region of the design space. We then bridge theory and practice by characterizing the architectural and governance elements that enable OPFEs, mapping them onto Bluesky and the AT Protocol, and illustrating the end-to-end lifecycle of a complete OPFE design. Overall, this work establishes OPFEs as a practical methodological paradigm for independent, transparent, and ecologically grounded experimentation on open social media.

Access to academic support is a key determinant of student success, yet students experience it unequally: some readily seek help from lecturers or tutors, while others hesitate due to anxiety, fear of judgement, uncertainty about expectations, or low confidence in their understanding. This may be especially evident in computing education, where programming tasks are cumulative and cognitively demanding. Although students increasingly turn to general-purpose generative AI tools, these can produce responses that are inaccurate, insufficiently contextualised, or misaligned with module expectations. This study presents and evaluates Beacon, a course-specific Retrieval-Augmented Generation (RAG) system providing private, immediate, module-aligned academic support. Grounding responses in approved teaching materials, Beacon was designed to lower barriers to help-seeking while encouraging independent learning. Using a design-based research approach, Beacon was developed iteratively and evaluated via mixed methods, combining questionnaires and semi-structured interviews with students and staff at a Higher Education institution. Students described Beacon's responses as closely aligned with module content and more trustworthy than unrestricted generative AI tools, valuing its use of pseudocode and scaffolded explanations over direct solutions. Although participants remained cautious about trusting AI-generated responses without verification, they viewed the system as a valuable first point of support before consulting lecturers or official resources. The findings suggest that carefully designed course-specific AI systems may reduce barriers to academic support by occupying an intermediary space between independent study and formal support. Rather than replacing educators, educational AI may be most valuable when it broadens access to guidance while preserving the pedagogical role of lecturers.

Generating natural co-speech gestures from streaming speech is essential for embodied conversational agents, where motion must be produced while a user is still speaking. Recent streaming gesture systems make online generation possible by autoregressing over discrete motion tokens, but this design compresses high-dimensional continuous motion into finite codebooks and can limit the realism and diversity of generated gestures. To preserve both causality and continuous expressiveness, we propose GestureFAR, a flow-autoregressive framework for streaming co-speech gesture generation. First, GestureFAR autoregresses over causal continuous motion latents, using a transformer to model streaming audio-motion context and a per-token flow-matching head to sample the next latent from a continuous distribution. Second, we introduce a head-only flow distillation strategy that freezes the causal backbone and distills the multi-step per-token flow head into a single network evaluation using consistency and distribution-matching objectives. This keeps the model token-causal while removing the main latency bottleneck for live interaction. Experiments on BEAT2 show that GestureFAR significantly improves the quality–latency trade-off among streaming-capable methods, preserving strong gesture quality while enabling real-time token-causal generation. Project Page: https://andypinxinliu.github.io/GestureFAR

Research on explainability in recommender systems largely centers on end users, overlooking the perspectives of those who build and maintain these systems and their potential use cases such as model debugging. In this study, we examine how news engineers and related technical stakeholders perceive and implement personalization and explainability in practice. We conducted 15 semi-structured interviews across nine news organizations, spanning diverse regions in both public and private sectors, to investigate the challenges and motivations shaping their approaches. Our findings reveal that personalization is not always a straightforward or desirable choice for news organizations, as concerns around user tracking, editorial control, and resource constraints often limit its adoption. Even among organizations implementing personalized news recommender systems in production, explainability is rarely prioritized, with day-to-day operational demands frequently taking precedence over longer-term transparency goals. Definitions of explainability vary widely across organizations, though some demonstrate promising internal practices and visualization tools that facilitate communication between engineering teams and newsrooms. Based on our analysis, we provide actionable and practical guidelines for news engineers and researchers on how to adopt explainability methods within a news personalization pipeline.

People increasingly compete against AI agents rather than other human opponents. We distinguish two channels: an opponent effect and an information effect. These are different elements with different consequences: the opponent effect is specific to a given computational system, the information effect a property of the information environment that an organisation or policymaker can control. We separate them in a preregistered experiment (N = 1,395) using a dynamic all-pay auction, a repeated contest in which escalation of commitment arises from the incentives. What participants are told about the opponent (human, an AI trained to imitate people, or an AI trained to compete well) is varied and crossed with who they actually face, in a deception-free design. What people are told influences escalation: the median price rises by 6.7 points when a human might be the opponent and falls by 8.8 when an optimising machine might be, a spread of about 15% of the prize value of the competition, produced by information alone. Competing against the AI agents lowers prices, yet reduces the chance that both sides finish with positive earnings, showing distinct effects of the opponent channel. The information effect is not explained by articulated strategy, or individual differences, and is consistent with a competitive response engaged when a human is a live possibility. This shows that describing an AI competitor is not behaviourally neutral.

Silent speech interfaces (SSIs) enable private communication without audible speech and may support people with post-stroke dysarthria. Everyday reuse requires articulation-related representations that generalize across days despite sensor repositioning and physiological changes. We present AESSI, an around-ear SSI using masked-context representation pretraining (MCRP): a student predicts teacher representations from masked time-frequency inputs to encourage robustness to recording variability. We collected 44 electrophysiological recordings from 24 participants for 25 everyday Mandarin sentences. With six participants' complete final recordings held out, AESSI achieved 92.24 percent mean accuracy without test-day calibration. AESSI exceeded the best adapted baseline by 50.57 percentage points. At least 21 days after each participant's last recording, five participants each completed 50 independently randomized online tests without calibration, achieving 98.0 percent overall accuracy. Median preprocessing and inference time in CPU replay was 31.70 ms. These results demonstrate end-to-end system operation and support online reuse without test-day calibration. Demo is included with the paper.

Underwater robot development is often hindered by the complexities of waterproofing and wiring, which significantly delay the rapid prototyping process. This paper presents MarineCraft, a modular toolkit designed to accelerate the development cycle through structural reconfiguration. The system features self-contained, waterproof propulsion modules that integrate power, wireless communication, and actuation. By eliminating centralized wiring and the need for repeated sealing, MarineCraft allows diverse robot geometries to be assembled and tested in minutes rather than days. Experimental results demonstrate that this reconfigurable architecture enables fast, iterative design cycles while maintaining reliable operation and leak-free performance at depths of up to 2.5 meters. Our toolkit effectively lowers the barrier to underwater robotics by transforming modularity into a vehicle for rapid physical prototyping.

Social Proactive Intelligence (SPI) extends proactive assistance beyond task completeness to consider social appropriateness in diverse embodied scenarios. However, prior SPI research faces two key limitations. First, existing work focuses on static images, whereas dynamic videos provide crucial cues for inferring human states and needs, offering richer information than isolated images. Second, prior work often relies on free-form data collection pipelines, which fail to guarantee comprehensive coverage of diverse scenarios. To address these gaps, we introduce RobotEQ-Video, shifting the focus from image-centric to video-centric analysis. To ensure comprehensive video coverage, we construct a hierarchical world-state taxonomy organized into a four-level coarse-to-fine structure, comprising 6 domains, 20 dimensions, 142 level-1 attributes, and 816 level-2 attributes. The resulting benchmark comprises 2K+ videos with 100K+ human annotations and 16K+ labels for assessing behavior properness. Benchmark evaluation reveals that current systems remain unreliable and fall short of human performance. We further explore how world models can help tackle this task. This work advances SPI research from static images to dynamic videos and ensures more comprehensive scenario coverage during benchmarking.

Generative User Interfaces (GenUIs) enable applications to generate interfaces on demand from user needs and context. Like conventional UIs, they must still reflect designers' intent and conform to requirements such as brand identity. Unlike conventional UIs, designers cannot directly specify or see every interface a GenUI may produce, making design intent harder to enforce. We introduce GUIDE (GenUI Development Environment), a system that lets designers continuously inspect and refine GenUI behavior as they create and edit interfaces. GUIDE uses designers' modifications and interactions to adapt GenUIs through prompt optimization and a novel adaptive conformance scoring model. We validate GUIDE's scoring model and system. The scoring model matched or outperformed proprietary LLM baselines on held-out comparisons of real and synthetic application screens. In a study with 12 UI/UX practitioners, participants found GUIDE effective and usable and significantly preferred aligned outputs over a strong baseline using exemplars and a model-generated design.md.

Effective collaboration and communication are vital to developer productivity and well-being, yet remain constrained by human factors such as attention, intrinsic motivation, and interpersonal accountability. These constraints are particularly vital for developers identifying with Attention Deficit Hyperactivity Disorder (ADHD), who navigate persistent environmental barriers in modern hybrid workplace settings. While developers with ADHD frequently rely on collaborative copresence practices (such as body doubling or pair programming) to support executive function, the recent emergence of agentic AI coding assistants has begun reshaping these collaborative dynamics. To investigate how developers with ADHD engage in human and AI-based copresence practices, we conducted semi-structured interviews with 14 software engineers with ADHD. Our findings reveal that while traditional human-human copresence provides critical social support and onboarding structure, it forces developers to constantly manage professional reputation and sacrifice personal privacy. Conversely, developers leverage emerging human-AI copresence to maintain accountability and cognitive flow without the social anxiety, performance judgment, or surveillance associated with human observation. Based on these empirical insights, we map developer copresence practices onto core dimensions of Goffman's copresence theory and Forsgren et al.'s SPACE framework of developer productivity, and provide design recommendations for AI-based tools that promote inclusive collaboration for developers with ADHD.

Technology increasingly supports self-care for understanding and improving one's own mental health. HCI is at the center of the turn towards self-care technology, yet we lack an account of who these interventions serve, what practices they support, how technology mediates those practices, and assumptions underlying design for self-care. In order to characterize the current landscape and inform future research, we analyzed 91 SIGCHI papers that contribute HCI interventions for mental health self-care from the ACM Digital Library from 2015 through June 2026. Then, we conducted an interpretive synthesis to surface six orientations of self-care, which describe how HCI self-care interventions constitute care through shared assumptions regarding self, care, and technology. Overall, our work provides an interconnected vocabulary for positioning HCI mental health self-care, highlights changing responsibilities of care towards users, and discusses implications for providing a more situated account of HCI self-care technology in addressing the 'general' user.

Cooperative and connected automated vehicles (CAVs) rely on Signal Phase and Timing (SPaT) messages to cross signalized intersections; a denial-of-service (DoS) flood that blocks SPaT forces CAVs into a fail-safe mode. Because human-driven vehicles share the intersection, the safety consequence depends not only on the attack and the CAV fail-safe policy, but on how the surrounding human drivers behave. We investigate this human-factors dimension with a coupled OMNeT++/INET (5G NR-V2X) and SUMO microsimulation of a signalized corridor, sweeping CAV market penetration (10-90%), four calibrated driver temperaments (cautious to aggressive) and two standards-based fail-safe policies, a minimal-risk maneuver (MRM) and an adaptive cruise control (ACC) keep-driving fallback, with each attack arm differenced against its policy-matched no-attack baseline. Temperament's effect on the attack is specific and modest rather than a blanket amplification. Aggressive surroundings worsen one metric, the hard-braking a keep-driving fail-safe forces on nearby drivers (p = 0.03), rising from near zero to +8 episodes/1000 veh-s. They appear to dampen rear-end conflicts, but only because the flood clears the queues aggressive drivers build, so the gain is in flow, not safety. On the attack's primary signatures, CAV red-light running and crossing conflicts, temperament has no detectable effect. It instead dominates baseline risk, producing a 13- to 18-fold cautious-to-aggressive gradient far larger than the attack itself, which acts through a channel already congested by CAV adoption. Human driver populations determine how dangerous the intersection is but do not systematically amplify this attack, so fail-safe design cannot assume a cautious test population bounds the risk.

Service applications for human-robot interaction are commonly written against the hardware-specific interfaces of one platform, so a change of hardware forces a rewrite of the application. The Robotic Interaction Service (RoIS) Framework 2.0, standardized by the Object Management Group (OMG), addresses this fragmentation by defining a platform-independent model in which Service Applications interact with Human-Robot Interaction (HRI) Engines through standardized interfaces and hardware-independent symbolic messages. A specification alone, however, does not provide the maintained implementation, Software Development Kits (SDKs), and adapters needed for practical adoption. This paper presents OpenRoIS, a community-driven open-source middleware providing a concrete implementation of the RoIS Framework 2.0. It takes the position that an openly developed, paradigm-neutral implementation is what carries the standard from specification to practice. OpenRoIS contributes a recursive engine architecture in which a single engine class realizes the main and sub HRI Engine roles, an internal five-method component contract distinct from the five external RoIS interfaces, a mapping of those interfaces onto JSON-RPC 2.0 over WebSocket, a single-source-of-truth type pipeline that generates three consistent language stacks, TypeScript and C# client SDKs that include web and Unity support, and a Python adapter SDK that includes ROS 2 support. Through the common RoIS interfaces, a Service Application can address physical robots and virtual agents over the internet. All source code, interface types, and documentation are released under the Apache-2.0 license and openly developed at https://openrois.org/.

As language models (LMs) rise in prominence, there is interest in making them more transparent in order to better understand their internal behavior. Recent interpretability work has focused on using sparse autoencoders (SAEs) to break down neuron activations at a given layer in the LM into human-understandable features, where each feature represents a concept that the model has learned. In this paper, we share work on using SAEs to analyze the behavior of text classification LMs. We present techniques for exploring the relationships between the SAE's features and the model's predictions and errors. We integrate these techniques into SAEfarer, a tool for analyzing concepts learned by text classification LMs. We assess SAEfarer in an expert pilot evaluation with five Ph.D. students.

Learning analytics dashboards (LADs) are intended to help students make sense of their learning data to support reflection and decision-making. However, their visualisations can be complex, particularly for students with low visualisation literacy. Narrative techniques, such as annotated charts and data comics, have been used to communicate insights directly, but not as supplementary materials to empower students to explore their visualisations themselves. In response, we conducted a qualitative study examining how data comics can complement LADs. We interviewed 18 nursing students and 4 of their teachers about a multimodal LAD containing visualisations with data comics explaining them. Analysis showed that data comics were clear, engaging, and helped make complex visualisations more accessible, though they must be carefully designed to avoid overwhelming students with information. The findings suggest that both students and teachers are receptive to data comics as a means of supporting the interpretability of LADs.

AI productivity is often measured by task completion time, economic value, or improvements in outcome quality. However, these measures usually treat collaboration as a black box where they capture what output was produced, but not the interaction cost required to produce it. Motivated by economics literature, we introduce a productivity-oriented framework for evaluating human-AI collaboration as outcome quality relative to interaction cost. Across two datasets spanning four tasks, we show that: (1) sessions with identical quality ratings can differ by up to 70 times in interaction cost; (2) quality-cost relationships vary by task, with some tasks rewarding extended interaction and others favoring fast convergence; (3) subjective user ratings are not reliable substitutes for productivity; and (4) productive sessions are characterized by agents probing earlier and users spending less effort repairing the interaction. By distinguishing productive success from costly success, our framework makes interactional cost visible and shows how dialogue analysis can inform the evaluation and design of AI systems.

Generative AI (GenAI) can support open-ended learning through generation, personalization, and learner modeling, yet educators need ways to shape these capabilities around educational goals. Through interviews and design activities with 15 U.S. educators, we examined educator configuration of GenAI using K-12 career exploration as an exploratory context. Educators configured not only AI-generated experiences, but also when student activity became an inference, whether learner information persisted, who could access it, and how it informed subsequent human action. They also faced challenges translating teaching needs into configurations: recognizing possibilities for control beyond familiar uses of GenAI, decomposing general-purpose AI into understandable functions and responsibilities, and identifying useful information through intended teaching actions. We discuss how GenAI systems can support educators in expressing and testing configurations, while establishing boundaries around personalization, inference, persistence, disclosure, and action to keep AI-supported learning aligned with evolving learner needs.

As generative AI is increasingly used as a source of personal financial guidance, understanding how people appraise such advice is important for supporting appropriate reliance. We conducted a randomized vignette experiment with 285 U.S. adults across eight financial decisions, independently varying three advice styles—AI, expert, and online community—and displayed source labels while holding the underlying recommendation consistent. Advice style most strongly shaped message and safety appraisals, Expert labels selectively increased perceived source knowledge, and decision context primarily shaped risk and safety appraisals. These appraisals were associated with downstream judgments, with models explaining 69.2% of overall quality, 75.9% of trust, and 82.9% of intended reliance. Expert-style advice also remained most preferred when shown without source labels. Our findings have implications for understanding financial advice evaluation, distinguishing the roles of advice style and source labels, and designing financial AI that supports grounded evaluation rather than simply maximizing trust.