跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+92新增 AI 导读

arXiv 最近完成扫描:2026-11-23 01:07 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-22 04:30 — 2026-11-23 04:30(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-23 01:07最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 671 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-23 01:05(北京时间)
新论文 · v1arXiv:2611.19652

LLM Facilitation of Group Decision-Making

José Córdova, Chun-Wei Chiang, Miriam Schirmer, Ming Yin, Emőke-Ágnes Horvát

原文摘要

Human groups often fail to integrate information distributed across their members, converging on incorrect decisions. We ask whether large language models (LLMs) can help groups reach the correct decision in such settings. In an online, chat-based experiment, 138 three-person groups (N = 414) completed a hidden-profile hiring task that required selecting the best candidate using public information available to all group members and private information available only to individual members. The randomized human-subject experiment included three conditions: no facilitation, an individual-level LLM that messaged each member privately, and a group-level LLM that messaged the whole group. The LLM facilitation consisted of adaptive interventions that summarized the discussion, nudged quiet members, and played devil's advocate. The LLM did not know which candidate was correct. Both LLM conditions significantly increased the rate at which groups reached consensus on the correct candidate, from 32.6% without facilitation to 56.5% with LLM facilitation. LLM-facilitated groups exchanged more consensus messages signaling agreement on the group's choice. Participants in the group-level condition also disclosed significantly more information about the correct candidate, whereas those receiving individual-level facilitation repeated public information less often. Finally, group-level facilitation received more favorable usability ratings than individual-level facilitation. These results show that LLMs can deliver adaptive, theory-informed interventions that improve group decision-making, and that the design of these interventions may shape how people respond to them.

cs.HC

新论文 · v1arXiv:2611.19601

Are Average Estimates in Line Graphs Biased Toward Areas of Higher Variability?

Sheng Long

原文摘要

When estimating the average value of a data series in line graphs, do viewers systematically overweight regions of higher variability? This is the question that Moritz et al. [14] set out to answer, and across two preregistered experiments they reported evidence for a bias they termed variability overweighting. Using their released data and code, I first reproduce their reported analysis, then ask whether their inference survives an equally valid analytic choice: measuring estimation error against the average of the displayed marks of each stimulus, rather than against a reference series that, for one mark type, is never shown. Under this alternative operationalization, the effect is substantially reduced and, for one mark type, reverses. Splitting the analysis by whether variability appears in the upper or lower region of the graph further reveals an asymmetry that the original direction-corrected analysis collapses away. I argue that the deeper issue is what verbal theories leave unspecified. When a theory is silent about which operationalization it requires, the metric ends up doing the theory's arguing for it. I close with a discussion of what reproduction and reanalysis are for: not verdicts on truth, but instruments for making analytic contingency visible and for forcing theories to say more.

cs.HC

版本更新 · v3arXiv:2411.15533

Development of a Low-Cost Prosthetic Hand Using Electromyography and Machine Learning

Mosab Diab, Ashraf Mohammed, Yinlai Jiang, Sharief Babikir

原文摘要

Electromyography (EMG) is a measure of muscular electrical activity and is used in many clinical/biomedical disciplines and modern human computer interaction. Myo-electric prosthetics analyze and classify the electrical signals recorded from the residual limb. The classified output is then used to control the position of motors in a robotic hand and a movement is produced. The aim of this project is to develop a low-cost and effective myo-electric prosthetic hand that would meet the needs of amputees in developing countries. The proposed prosthetic hand should be able to accurately classify five different patterns (gestures) using EMG recordings from three muscles and control a robotic hand accordingly. The robotic hand is composed of two servo motors allowing for two degrees of freedom. After establishing an efficient signal acquisition and amplification system, EMG signals were thoroughly analyzed in the frequency and time domains. Features were extracted from both domains and a shallow neural network was trained on the two sets of data. Results yielded an average classification accuracy of 94.8% and 93.2% for the time and frequency domains respectively. Furthermore, results showed a faster computation and response for the time domain analysis; hence, it was adopted for the classification system. A wrist rotation mechanism was designed and tested to add significant functionality to the prosthetic. The mechanism is controlled by two of the five gestures, one for each direction. Which added a third degree of freedom to the overall design. Finally, a tactile sensory feedback system which uses force sensors and vibration motors was developed to enable sensation of the force inflicted on the hand for the user.

cs.RO · cs.HC

新论文 · v1arXiv:2611.19564

Behavioral Assurance for Socially Deployed AI Agents

Nicole H Brennan, Jiaee Cheong

原文摘要

AI agents are increasingly deployed in socially consequential settings, yet existing evaluations provide limited assurance that they behave consistently with their intended characteristics across diverse interactions. We introduce an evaluation framework for measuring the behavioral consistency of socially deployed AI agents. The framework operationalizes agent behavior along five measurable axes and uses a standardized evaluation battery spanning six socially salient interaction settings to assess behavioral differentiation, consistency, and drift. Controlled persona configurations serve as experimental anchors, enabling systematic testing of whether intended behavioral differences persist across contexts rather than appearing only as stylistic variation. Preliminary analyses demonstrate measurable differentiation across configurations and suggest associations between behavioral profiles and interaction outcomes. By shifting the focus from persona design to behavioral assurance, this work provides a foundation for evaluating whether socially deployed AI agents behave as intended, consistently and measurably, across the situations in which users encounter them.

cs.AI · cs.ET · cs.HC · cs.MA

新论文 · v1arXiv:2611.19474

Towards Informed Autonomy Design: Understanding the Interplay of Function Characteristics and Autonomy Preferences in Automotive Agents

Sebastian Zepf, Annika Stampf, Markus Schuster, Enrico Rukzio, Mark Colley

原文摘要

Proactive, autonomous interactions receive high interest in the field of intelligent assistants, including the automotive domain. A central challenge, however, is identifying appropriate levels of autonomy for different functions while maintaining user acceptance and trust. This work examines how function characteristics relate to suitable autonomy levels and whether these relationships generalize across functions. We conducted an expert workshop to define autonomy levels and identify relevant function characteristics. We then collected data from 126 participants, who rated 14 in-vehicle functions regarding autonomy preferences and function characteristics, from which we trained machine learning models to predict appropriate autonomy levels. Building on our findings, we developed our prototypical Autonomy Design Assistant that supports designers in making autonomy-related decisions, which we evaluated qualitatively with nine experts. Our results suggest that function characteristics can rank functions by their suitable level of autonomy and thereby guide more informed autonomy design decisions, whereas predictions for individual users remain uncertain.

cs.HC

版本更新 · v5arXiv:2303.17707

Stop Using Plausibility as the Criterion for Explainable AI

Weina Jin, Xiaoxiao Li, Ghassan Hamarneh

原文摘要

Explainable artificial intelligence (XAI) is motivated by the problem of making AI predictions understandable, transparent, and responsible, as AI becomes increasingly impactful in society and high-stakes domains. The evaluation and optimization criteria of XAI are gatekeepers for XAI algorithms to achieve their expected goals and should withstand rigorous inspection. To improve the scientific rigor of XAI, we conduct the first comprehensive and critical examination of a common XAI criterion: plausibility. Plausibility assesses how convincing the AI explanation is to humans, and is usually quantified by metrics of feature localization or feature correlation. Our examination shows that plausibility is an invalid measure of explainability, and human explanations are not ground truth for XAI, because both ignore the necessary assumptions of explanation. One fundamental assumption is that AI explanations are supposed to behave adversarially, analogous to auditors' or doctors' roles of identifying potential problems. Evaluating or optimizing XAI to generate more plausible explanations is analogous to incentivizing (i.e., bribing) auditors/doctors to generate more positive reports, which is different from encouraging AI models to learn more plausible features (analogous to encouraging companies/patients to improve their conduct/health). Our examination further reveals the consequences of using plausibility as the XAI criterion, including increasing misleading explanations that manipulate users, deteriorating users' trust in the AI system, undermining human autonomy, being unable to achieve complementary human-AI task performance, and abandoning other possible approaches of enhancing understandability. Due to the invalidity of measurements and the unethical issues, this paper argues that the AI community should stop using plausibility as the criterion to evaluate and optimize XAI algorithms.

cs.AI · cs.HC

版本更新 · v4arXiv:2504.03253

picoRing mouse: ultra-low-power ring-based wireless tinymouse

Yifan Li, Masaaki Fukumoto, Mohamed Kari, Shigemi Ishida, Akihito Noda, Tomoyuki Yokota, Takao Someya, Yoshihiro Kawahara 等 9 位作者

原文摘要

Wireless mouse rings offer subtle, reliable pointing interactions for wearable computing platforms. However, the small battery below 27 mAh in the miniature rings restricts the ring's continuous lifespan to just 1-10 hours, because current low-powered wireless communication such as BLE is power-consuming for ring's continuous use. The ring's short lifespan frequently disrupts users' mouse use with the need for frequent charging. This paper presents picoRing mouse, enabling a continuous ring-based mouse interaction with ultra-low-powered ring-to-wristband wireless communication. picoRing mouse employs a coil-based impedance sensing named semi-passive inductive telemetry, allowing a wristband coil to capture a unique frequency response of a nearby ring coil via a sensitive inductive coupling between the coils. The ring coil converts the corresponding user's mouse input into the unique frequency response via an up to 449 uW mouse-driven modulation system. Therefore, the continuous use of picoRing mouse can last approximately 600 (8hrs use/day)-1000 (4hrs use/day) hours on a single charge of a 27 mAh battery while supporting subtle thumb-to-index scrolling and pressing interactions in real-world wearable computing situations.

cs.HC

新论文 · v1arXiv:2611.19435

Security Authentication as Protective Friction: Understanding the Dual Effects of Authentication Measures in e-Government Platform

Jianshan Pan, Zongyi Chen, Qiyou Lin, Xiaofang Cai

原文摘要

E-Government platforms, such as government credit platforms, handle highly sensitive personal data, requiring stringent security authentication (e.g., facial recognition, multi-factor verification) that protects users but impedes their experience. Drawing on Tomalin's (2023) e-friction typology and the emerging literature on beneficial design friction, we reconceptualize these authentication measures as protective friction, a theoretically distinct form of non-elective, overt, impeding e-friction that serves a security-enhancing function. We propose a dual-pathway model in which protective friction simultaneously reduces privacy-security risk perception (protection pathway) and increases effort cost (cost pathway), with self-efficacy moderating only the risk pathway. This differential pattern suggests that what matters is not users' ability to overcome friction, but their comprehension of its protective purpose, a construct we term protective mechanism comprehension. We outline a mixed-methods research design combining a survey of platform users and semi-structured interviews with platform staff at a Chinese municipal credit center to test this model. This research-in-progress contributes to IS theory by extending e-friction research from conceptual typology to empirical investigation, identifying when security friction becomes beneficial rather than burdensome.

cs.CR · cs.HC

新论文 · v1arXiv:2611.18439

在义务与证据之间:将欧盟人工智能法案转化为技术要求的参与式研究

Between Obligations and Evidence: A Participatory Study of Translating the EU AI Act into Technical Requirements

Helma Torkamaan, Masoud Mansoury, Yanan Xin, Oscar Oviedo Trespalacios, Roberta Savella, Andrej Zwitter, Maria Heuss, Huy Son Nguyen 等 12 位作者

AI 速读 基于摘要

通过32名跨学科参与者的工作坊,探讨将欧盟AI法案的高风险系统要求转化为可测量技术要求和合规证据时面临的解释性、组织性与证据性挑战。

cs.CY · cs.AI · cs.HC · cs.SE

查看原文摘要

The EU AI Act imposes technical and organizational requirements for high-risk AI systems, but applying these requirements involves contextual choices about what to measure and what evidence supports a compliance claim. We investigate these challenges through a participatory workshop involving 32 researchers, policymakers, and practitioners from different disciplines, using realistic scenarios in healthcare, recruitment, and public transport to examine how regulatory obligations are interpreted, translated into technical requirements, and evaluated in practice. Through a thematic analysis of workshop data, we identify recurring tensions between how regulatory obligations are translated into measurable system properties, how responsibility and human oversight are exercised in practice, and how the validity of compliance evidence is affected by changing operational conditions and system uses. For example, participants highlighted how fairness metrics could conceal discrimination in recruitment, how time pressure and limited information could undermine human oversight in public transport, and how changes in patient populations could invalidate previously established evidence of system performance. Our findings suggest that technical, organizational, and evidentiary challenges are interdependent, and that establishing and maintaining compliance requires attention not only to technical assessments but also to how AI systems are used, governed, and monitored over time. We discuss implications for supporting context-sensitive and ongoing compliance.

新论文 · v1arXiv:2611.18438

面向混合现实头显的物理教具无标记6DoF跟踪初步研究

Toward On-Device Markerless 6DoF Tracking of a Physical Manipulative on a Mixed-Reality Headset: A Preliminary Study

Guangxi Feng, Philip Yasskin, Wei Yan

AI 速读 基于摘要

作者在Meta Quest 3上为乐高飞机开发无标记6DoF跟踪器,用合成渲染训练的YOLO预测关键点并结合PnP求解位姿,并报告了合成验证集上的检测与关键点指标及初步头显测试表现。

cs.CV · cs.HC

查看原文摘要

AR-Classroom uses physical models and virtual overlays to help learners explore spatial transformations. To align these overlays on a standalone headset, we developed a markerless six-degree-of-freedom(6DoF) tracker for a LEGO airplane on the Meta Quest 3. A compact YOLO model trained on synthetic Unity renders predicts 20 keypoints from dynamic RGB crops resized to 128 by 128 pixels. A perspective-n-point solver estimates the airplane's pose from these predictions and the corresponding 3D landmarks. In a paired evaluation on 1,000 synthetic validation images, cropping guided by ground-truth boxes increased the detection rate on annotated images from 32.5 to 46.2 percent. Mean keypoint F1 increased from 42.9 to 44.6 percent, with lower keypoint precision in the cropped view. In preliminary headset tests, 2 Hz was the highest tested tracking target at which the application maintained approximately 72 frames per second. A headset demonstration illustrates virtual overlay alignment with the physical airplane before and after a manual rotation. Quantitative 6DoF pose accuracy on real headset footage will be measured in future work.

新论文 · v1arXiv:2611.18385

Voice-Based Conversational Agents as AI Care Assistants: Evaluating Personalization, Intervention Delivery Fidelity, and Privacy Expectations in Older Adults' Care

Thalia Viranda, Shupeng Wang, Jia Bo, Yuchen Yang, Hongjiao Zhang, Andrea Cuadra, Daniel A. Adler, Walter Boot 等 11 位作者

原文摘要

Generative AI enables voice-based conversational agents to play more active roles in older adults' care, including personalizing support and operating alongside clinicians and care partners. This shift creates two challenges: how to personalize support while faithfully delivering evidence-based interventions, and how to manage personal-data use and sharing across AI and care stakeholders. We designed and evaluated ARC, a voice-based conversational agent that operationalizes multidomain lifestyle intervention through sessions with predefined goals, participant context, and evidence-based components. In a 3-day remote study, 80 older adults completed 473 sessions across six session types (9,183 turns; averaging 19.4 turns and 6 minutes per session). Participants reported favorable usability, acceptability, and use intentions. System-level analyses showed strong domain-level but modest participant-specific contextual reuse, no significant personalization-fidelity association, and fidelity limitations centered on incomplete delivery of intervention components rather than off-protocol drift. Within care relationships, expectations for personal-data use and sharing varied by data type and recipient. Our findings support feasibility of conversational delivery of multidomain lifestyle intervention, offer methods and system-design insights for longitudinal evaluation, and motivate an evaluation agenda for generative AI health interventions: user-experience and outcome measures should be complemented by evidence of whether intended intervention processes were delivered as designed.

cs.HC

新论文 · v1arXiv:2611.18284

Clean Tickets, Wrong Orders: Catching Silent Errors with a Language Model in Your Browser Tab

Umar Ahmed, Maxim Dunaev, Mohammad Nour Al Awad, Sergey Ivanov, Ivan Khodnenko

原文摘要

A small language model that turns a typed order into structure can fail in two ways. It can print something broken, which any system rejects. Or it can print a clean, well formed order that nobody placed. Our companion work calls the second kind a silent error, and it is the dangerous one. We present a web demo in which a fine-tuned 0.8B parameter model runs entirely inside the visitor's browser tab, through llama.cpp compiled to WebAssembly. No order text leaves the device. The page parses orders as the visitor types, scores every ticket with the PIZZA benchmark's own matcher ported to TypeScript, refuses anything off the menu with "?" so the model can face the open web, and lets visitors hunt for silent errors or try to cause one. Run in the browser on all 1,357 PIZZA test orders, the deployed model writes the same output as the server evaluation for 99.0% of them and reaches the same exact match (0.882); we also report its latency on 3 consumer laptops. Demo: https://wrong.cuyor.com

cs.LG · cs.CL · cs.HC

新论文 · v1arXiv:2611.18230

Personalization of Basic and Moral Values Guiding LLM-Controlled Assistant Robots

Mateusz Wozniak, Qi Gao, Agnieszka Wykowska

原文摘要

Personal assistant robots powered by large language models (LLMs) are likely to enter everyday life within the next decade, but the values that should guide their behaviour remain largely unspecified. Current alignment practice steers a single model toward an aggregate of human values, ignoring that individual users may prefer a robot whose value profile differs from their own. We administer parallel self- and robot-targeted versions of three established psycho-metric instruments - the simplified Schwartz Values Survey (SVS), the Portrait Values Questionnaire (PVQ-21), and the Moral Foundations Questionnaire (MFQ) - to potential future users (N=22), capturing both their personal values and the values they would want an assistant robot to embody. We compare the three instruments as personalization tools using the UEQ-S and benchmark fifteen contemporary LLMs against the resulting profiles. Participants wanted their robot to score markedly lower than themselves on personal-focus values and higher on social-focus values; moral profiles were nearly identical. LLMs prompted to act as robots shifted only weakly toward the desired profile, indicating that default model behaviour and prompt engineering are no substitute for explicit value personalization.

cs.HC · cs.AI

版本更新 · v2arXiv:2611.16931

Beyond Curiosity: Habit and Organizational Learning Capability as Predictors of Shadow AI

Nolan Lovett, Mohan Yang

原文摘要

Generative AI has entered the workplace faster than organizations can govern it. Employees may use AI tools their employer has not sanctioned and conceal that use, but the psychology of this behavior remains poorly understood. We compare an exploratory-disposition account with one centered on reported use and habit. Using survey data from 510 employed adults reporting workplace generative-AI use during the preceding 12 months, we estimated the unique and relative contributions of workplace curiosity, habit, technology-acceptance beliefs, and perceived organizational learning capability through hierarchical regression, bootstrap relative weights, and full-subset dominance analysis. Habit had the largest relative weight, accounting for 28.3% of explained variance, and completely dominated joyous exploration across all 512 possible predictor subsets. Joyous exploration contributed 3.4% and became nonsignificant when use behavior, performance expectancy, and social influence entered the model; habit subsequently explained additional variance. Organizational learning subscales accounted for 24.1% of explained variance; experimentation and knowledge transfer were associated with lower shadow AI, while curiosity-by-learning interactions were nonsignificant. Separate models for unauthorized use and concealment reproduced the habit-dominance pattern. Perceived professional support was associated with lower concealment, although its coefficient did not significantly differ between the two behavioral outcomes. Shadow AI in this sample was more strongly associated with self-reported habit strength and perceived organizational conditions than with exploratory disposition. The cross-sectional design does not establish causal or temporal order.

cs.CY · cs.HC

版本更新 · v2arXiv:2607.24558

Proceedings of The First Reflection in Creative Experience (RiCE) Workshop

Corey Ford, Olga Sutskova, Samuel Rhys Cox, Sarah Sterman, Max Kreminski, Rosa Van Koningsbruggen, Anqi Wang, Ege Otenen 等 15 位作者

原文摘要

Reflection and metacognition are central to the creative user experience. However, most HCI research on reflection focuses on clear, task-oriented goals such as to reflect on personal data or pedagogical outcomes. This contrasts with the open-ended and challenging to articulate goals of creative user experiences. For the first time, this workshop brings together interdisciplinary researchers, designers, educators, and artists across HCI, Cognitive Science, Design, AI, Learning Sciences, and Digital Art to examine reflection in creative interaction. The workshop will discuss themes, drawn from earlier discussions with HCI researchers and artists, on: how best to capture reflection in creative contexts, how to leverage the arts to support reflection for ethical change, and how to design creative AI that enhances - not hinders - critical thinking. By bringing interdisciplinary perspectives on reflection into discussion, the workshop will develop a guiding taxonomy for reflection in creative interaction to inform future creative practice and tool development.

cs.HC

版本更新 · v2arXiv:2610.00073

A Comprehensive Evaluation Framework for Conversational Home Energy Management Systems

Wooyoung Jung

原文摘要

The growing complexity in home energy management (HEM) demands advanced systems that guide occupants toward informed energy decisions reflecting their background, preferences, and context. Large language model (LLM)-integrated HEM systems (HEMS) have demonstrated promise, but previous studies relied on single-turn or single-task evaluations with response accuracy as the primary metric. Whether such systems deliver effective interactions across the extended multi-turn dialogues typical of real-world use remains an open question. This study introduces a comprehensive evaluation framework of LLM-integrated HEMS derived from the Goal-Question-Metric methodology, organized across five categories: task performance, factual accuracy, interaction quality, control capability, and system efficiency. A total of 23 metrics across multi-turn conversations are proposed and an LLM-as-judge pipeline is employed to enable scalable automated scoring. Its reliability is validated against three trained human coders: after iterative rubric calibration, twelve of the fifteen LLM-scored metrics reached strong agreement (ICC >= 0.73), three of them perfect, while the remaining three exhibited near-zero variance in human scores and are instead reported via mean absolute error (0.04-0.28). To demonstrate the framework's effectiveness, 970 dialogues -- 16 scenarios and five personas -- were generated and evaluated across four conversational HEMS configurations spanning a sophistication gradient, from a vanilla LLM with raw energy data to a multi-agent HEMS. The framework distinguished the four configurations across multiple evaluation dimensions, revealing their respective strengths and weaknesses. This study contributes to conversational HEMS by providing a reproducible, multi-dimensional evaluation methodology that comprehensively assesses sustained, context-aware system performance.

cs.HC

新论文 · v1arXiv:2611.17874

What a Memory Preview Cannot Tell You: Ambiguity in AI Memory Permissions

Sadia Noman Tonni, Nafis Fuad Shahid

原文摘要

A memory rule states when an assistant may reuse a remembered event, and an editor can confirm a rule by previewing one use it allows and one it blocks. We ask what such a preview lets a person infer about the rule they saved. For an editor with six or twelve valid rules, we enumerate every rule compatible with a preview. Splitting the rules most evenly does not target the question a user cares about. For an explicit preference, two adaptive tests leave all three recommendation scopes open (for a one-off choice the outcome turns on a tie), while one test of transfer to another task settles the question. Weak previews are also the default. Under the intended rule, 36 of 39 possible allowed/blocked pairs contain a blocked example that no rule allows, and no pair identifies the rule. Three or four tests suffice here; when permissions depend on each other, a fixed checklist grows to six or nine and adaptive questioning needs at most five or seven. These counts use a specified rule vocabulary and fictional events. In a small pilot, 10 of 20 people who saw such a weak preview of a rule they had just chosen mispredicted, or were unsure about, at least one of two uses, and none of those 10 said the outcomes matched what they wanted. Whether better previews help people is untested.

cs.HC

新论文 · v1arXiv:2611.17856

DECODE: Diagnosing Interpretability Failures in Automated Interpretation Process

Dohyun Kim, Jaeung Lee, Donghee Hong, Jaemin Jo

原文摘要

Tools for interpreting the internal representations of Large Language Models (LLMs) increasingly rely on LLMs themselves to both generate and evaluate explanations, creating a self-referential automated interpretation process with minimal human oversight. This automation raises significant reliability concerns, which are exacerbated by the absence of ground truth. In practice, it is difficult to validate explanations or to attribute interpretability failures to their source -- whether they originate from the tool's extracted representations or from the LLM used in the process. To address these challenges, we present DECODE, a visual analytics system that reintroduces human oversight into the automated interpretation process. Our approach decomposes the diagnostic workflow into three progressive stages, isolating failure sources ranging from structural defects to explanation-level misalignments. Drawing inspiration from inter-coder consensus in qualitative analysis, we utilize consensus among independently generated explanations and their evaluation metrics as a proxy for reliability. To further scale human inspection, we employ a three-phase active seeding protocol that strategically recommends high-priority instances for manual review. Finally, we demonstrate the effectiveness of our approach through a case study on 16,384 Sparse Autoencoder features, showing that it can efficiently identify and attribute interpretability failures at scale.

cs.AI · cs.HC

版本更新 · v2arXiv:2502.20658

Curating Safe Spaces for Emotion Disclosure during Illness Recovery on Video-Sharing Platforms

Jiaying "Lizzy" Liu, Yunlong Wang, Allen Jue, Yao Lyu, Yiheng Su, Shuo Niu, Nathan TeBlunthuis, Yan Zhang

原文摘要

The advent of video-sharing platforms has transformed self-expression, transcending entertainment to encompass sensitive disclosures and emotional revelations. In this submission, we discuss our study on emotional disclosure by individuals with Schizophrenia through YouTube vlogs and its implications for designing safe online spaces.

cs.HC · cs.CY · cs.SI

新论文 · v1arXiv:2611.17830

Alleviating Interview Stress: Effects of Robot Persona and Reactive Backchanneling on High-Pressure Mock Interviews

Haochen Yang, Zhuoran Gao, Geqing Tao, Yusi Dong, Pei-Luen Patrick Rau

原文摘要

High-pressure job interviews induce anxiety and impair performance. Existing mock training suffers from a trade-off among cost, standardization, and physical presence. This study investigated how a robot interviewer's verbal persona (supportive vs. challenging) and nonverbal backchanneling (active vs. negative) affect users' psychological states and facial expressions in a simulated interview. In a 2x2 between-subjects experiment (N=28), participants interacted with a NAO robot. Subjective measures (state anxiety, self-efficacy, social presence) and objective facial emotion recognition were collected. Results showed that a supportive persona reduced task load, increased perceived robot warmth and mind perception, and decreased perceived surveillance and robot discomfort. Active backchanneling increased non-neutral (p = .021) and anxiety-tension facial affect (p = .048). A significant interaction effect between persona and backchanneling was found on social presence (p = .045). The subjective-objective consistency was 67.9%, indicating complementary measurement modalities. The findings provide preliminary support for the social buffering hypothesis in human-robot interaction.

cs.HC

新论文 · v1arXiv:2611.17802

Multimodal Person Concept Model for Person Identification under Varying Observation Conditions

Mizuho Okitani, Yoshinobu Hagiwara

原文摘要

Service robots in domestic and office environments must identify users to provide personalized services based on their preferences and previous interactions. This is challenging because only a few observations may be available for learning, while observation conditions change owing to appearance, environmental noise, and utterance content. To address this challenge, this study proposes a multimodal person concept model that learns person concepts from a small number of observations, without person labels, and enables robust identification under changing conditions. The model employs a nonparametric Bayesian generative model based on the Chinese restaurant process and integrates visual, acoustic, and linguistic features extracted using Contrastive Language-Image Pre-training (CLIP) and Contrastive Language-Audio Pretraining (CLAP), followed by principal component analysis (PCA). We evaluated six participants under eight conditions in which appearance changes, additive noise, and transcription errors were introduced individually and in combination. Averaged over the eight conditions, the proposed model achieved an identification accuracy of 0.89 while inferring the number of person concepts from the observations, which is comparable to k-means clustering that was supplied with the true number of participants (0.88). We also examined PCA dimensionality, modality availability, and variation strength, and demonstrated the model on a Toyota Human Support Robot. These results show that multimodal person concept learning supports robust person identification under changing conditions, and that identification can succeed even when the number of concepts is not correctly recovered. The project page and demonstration video are available at https://okitamisan01.github.io/person_concept/.

cs.RO · cs.AI · cs.HC · cs.LG

新论文 · v1arXiv:2611.17713

DesignSpecs: A DESIGN.md Dataset of Visual Design Specifications for AI Agents

Jialiang Wei, Walid Maalej

原文摘要

While AI agents increasingly generate and modify user interfaces, they rarely rely on a visual design specification for a certain project. The DESIGN$.$md format, which originated from Google's AI design tool Stitch and which was open-sourced in April 2026, addresses this gap by describing a visual identity through design tokens (such as named colors, text styles) and Markdown prose. To our knowledge, no large-scale research dataset of such design specification files exists. We present DesignSpecs, a dataset of 36,906 DESIGN$.$md files from 15,794 public, non-fork GitHub repositories, representing 17,240 unique file contents. We collected 613,207 files named DESIGN$.$md in October 2026. Because the same file name also denotes architectural plans and other design documents, we filtered those with YAML front matter, a design-system name, at least one recognized design token, and zero errors under the official linter. Our JSON Lines dataset provides file-level and deduplicated views of the original Markdown, links files to repositories, paths, and commits, and is released with related scripts. We outline research opportunities on visual design knowledge and design-aware AI agents. Dataset is available at: https://huggingface.co/datasets/Jl-wei/DesignSpecs

cs.SE · cs.HC

新论文 · v1arXiv:2611.17564

AI-Voyager: A Public-Interest System for Human-AI Civic Reasoning to Contest and Shape the Rules That Govern AI

Snehalkumar `Neil' S. Gaikwad, Dhruv Dixit, Bryen Alvarez, Pratik Patekar, Anika Sharma, Akshara Kolipaka, Paritosh Pandey

原文摘要

Governments are writing rules for artificial intelligence that decide what counts as an automated decision or a harm, often before the people they affect have a chance to question them. We introduce AI-Voyager, a public-interest system for human-AI civic reasoning, in which people and AI work together to understand, contest and shape the rules that govern AI. A resident can find their city's rules on AI in hiring or upload their country's AI strategy, read it as an affected worker would, open the passage behind any answer, and draft a revision. Its architecture turns 3,653 governance documents from city, state, federal and national governments into passages that keep their page and edition, and retrieves evidence through bounded agentic search that verifies each statement. On 360 new questions that require finding the relevant documents, it reached 83.0% macro recall, against 80.5% for the strongest baseline, 73.7% without iterative search and 99.1% on a benchmark with fixed documents. In a study with 24 participants new to two AI bills, most proposed changes asked how provisions would apply. Participants chose lenses for the kind of explanation they wanted, and citations signaled grounding but rarely led them to check the source. By binding AI assistance to the exact text of public documents, this work introduces a grammar of operations and a design space that inform how such systems are designed and evaluated, and how people take part in governing AI.

cs.AI · cs.CL · cs.HC

新论文 · v1arXiv:2611.17490

Learning Recommendations under Imperfect Human Compliance with Record-Level Differential Privacy

Yuwen Ma, Nicola Bastianello, Sarah Spurgeon, Boli Chen

原文摘要

This paper investigates human-in-the-loop recommendation systems, where effectiveness relies on human compliance and privacy concerns restrict the use of historical response data. The pro posed framework models the implemented action as a random response to the recommendation and formulates the recommendation mechanism as a decision-dependent optimisation problem under an unknown compliance distribution. A batched Gaussian process upper confidence bound algorithm is then adapted to learn from locally perturbed historical actions, providing privacy for individual raw records. The analysis establishes record-level differential privacy and derives high-probability simple regret bounds when the compliance distribution is unknown. These bounds characterise how privacy noise, batch size, and behavioural information affect the guaranteed quality of the learned recommendation. In particular, a known upper bound on the non-compliance rate enables the rec ommendation space to be screened before any private data are queried. Simulations of a fixed-state car-following problem with synthetic historical driver responses demonstrate the effectiveness of the proposed algorithm and verify the theoretical findings.

cs.HC

版本更新 · v4arXiv:2608.23642

AI Agents Push Humans Out of the Loop

Margaret Mitchell, Avijit Ghosh, Samir Passi

原文摘要

AI agents pose significant risks as they are granted increasing autonomy. A commonly proposed solution is human oversight and keeping a ''human in the loop'', but this is not a simple solution: Not only do current approaches to AI agent design impede effective human oversight, but the cognitive capacities required for it are also themselves degraded by extended use of AI systems. This position paper argues that current approaches to the development and deployment of AI agent systems do not support effective human oversight -- they contribute to its degradation. To address this, a top priority in the advancement of AI agents should be supporting the situated goals and cognitive requirements of effective human oversight, treating the human needs of overseers at the same level of importance as AI agent capability. To put this idea into practice, we connect work on automation and human-computer interaction to AI agent processes, outlining design-level affordances and organizational protocols that (1) support overseers in exercising critical judgement and (2) counteract the skill atrophy that arises from extended use of automation. We urge developers and deployers to adopt these or similar approaches. Without explicit support for the cognitive demands of effective human-agent interaction, AI agent systems will continue to passively incentivize the degradation of the very human skills they rely on.

cs.AI · cs.HC

版本更新 · v3arXiv:2606.00727

知道何时行动:交通中人类行为的证据累积模型

Knowing When to Move: Evidence Accumulation Models of Human Behavior in Traffic

Floor Bontje, Felix van Waveren, Leendert van Maanen, Bhargav Nallapu, Gustav Markkula, Arkady Zgonnikov

AI 速读 基于摘要

一篇半系统综述,梳理28项(2014–2026)用证据累积模型(EAM)刻画交通决策与操控行为的研究,并按建模层级与实现方式组织文献。

cs.HC

查看原文摘要

Evidence accumulation models (EAMs) describe decisions as noisy evidence accumulating toward a decision boundary. Although widely studied in laboratory tasks, their application to dynamic, real-world behavior has received less attention. Traffic offers a setting where evidence changes as situations unfold, response timing matters, and decisions occur within ongoing control and interaction. This semi-systematic review synthesizes 28 publications (2014-2026) that model traffic decisions and control actions with EAMs. We organize the literature by modeling level (discrete decisions versus continuous action control) and implementation (stand-alone accumulators versus models embedded in broader perception-action or interaction frameworks). We examine how model components are implemented and evaluated across tasks. Overall, EAMs account for a range of dynamic road-user behaviors. Several comparisons suggest that response timing is better described by accumulating evidence as situations develop than by fixed delays or thresholds on momentary evidence, although accumulation models do not consistently outperform other kinds of models. Whether decreasing boundaries improve the fit differs between studies, and the models offer testable accounts of how decision-relevant information is processed. For cognitive scientists, traffic offers a testbed for studying how evidence from changing environments shapes decision-making. For applied modelers, the findings show how EAM components can be adapted to different traffic tasks, and why the choice of components needs to be evaluated for each task. However, most publications that estimated parameters pooled across participants, and most were not tested beyond the data they were fitted to, highlighting the value of participant-level or hierarchical estimation and of testing on new data.

新论文 · v1arXiv:2611.17101

一种结合滤波器组卷积的紧凑型xDAWN引导时空网络用于P300检测

A Compact xDAWN-Guided Spatio-Temporal Network with Filter-Bank Convolution for P300 Detection

Mohammad Mahdi Habibi Bina, Mohammad Reza Daliri

AI 速读 基于摘要

作者提出一种仅含5100个可训练参数的紧凑深度学习架构,将xDAWN空间滤波、固定滤波器组与深度可分离卷积结合用于P300检测,并在两个公开基准上报告了准确率与速度的折中表现。

cs.HC · cs.AI

查看原文摘要

P300-based brain-computer interfaces (BCIs) enable communication by decoding stimulus-evoked EEG responses into character selections without requiring voluntary motor output. Reliable P300 detection remains difficult because of low response amplitude and signal-to-noise ratio, while practical spellers require accurate character selection with few stimulus repetitions and low computational cost. We propose a compact deep learning architecture that combines xDAWN spatial filtering for event-related potential enhancement and dimensionality reduction, a fixed frequency-selective filter bank, and convolutional feature learning for spatio-temporal EEG decoding. Depthwise-separable convolutions and progressive average pooling reduce computational complexity while retaining discriminative temporal information. The resulting target/non-target classifier contains only 5,100 trainable parameters. We evaluated the model on two public benchmarks, BCI Competition II Dataset IIb and BCI Competition III Dataset II, and compared it with established P300 decoding methods across different numbers of stimulus repetitions. The model achieved an information transfer rate of 17.8 bits/min with two repetitions on BCI Competition III and 40.5 bits/min on BCI Competition II, demonstrating a favorable accuracy-speed trade-off. These results suggest that combining domain-informed spatial and spectral priors with compact neural networks can support efficient P300 decoding for EEG-based BCI communication.

新论文 · v1arXiv:2611.17058

神经表征作为新的交互模式

Neural Representations as New Modes of Interactivity

Stanley Huang, Anthony Baez, Catherine Yeh, Pat Pataranutaporn

AI 速读 基于摘要

提出“神经表征交互”(NRI)范式,将神经网络内部表征视为用户可检视、引导和编辑的交互材料,并构建相应设计空间。

cs.HC

查看原文摘要

Human-AI interaction today runs almost entirely through prompts and outputs, keeping AI systems opaque to general users. We introduce Neural Representation Interaction (NRI), a paradigm that treats the internal representations of neural networks as an interaction material people can inspect, steer, and edit. Situating NRI alongside graphical, tangible, and bio-computer interaction, we argue that the concepts and algorithms models encode internally offer representational affordances for richer human-AI interaction. We synthesize actionable mechanistic interpretability methods and, drawing on General Morphological Analysis, construct a design space spanning Interaction, Target, Referent, and Purpose. Mapping existing interfaces onto this space reveals that most serve expert auditors, while few support lay users. We then present speculative applications in education, personal user modeling, and hiring audits, and discuss design principles, limitations, and sociotechnical risks. NRI offers HCI researchers abstractions for designing interactions that work with AI computation rather than only through its inputs and outputs.

新论文 · v1arXiv:2611.17018

探索面向包容性小组对话的社会可接受3D反馈设计

Exploring Socially Acceptable 3D Feedback Design for Inclusive Small-Group Conversation

Qianjie Wei, Yifan Li, Zhen Bai

AI 速读 基于摘要

该研究在XR小组对话场景中,探索如何通过幽默、降低社会注意和间接表达等策略设计公开3D反馈,使其既保持效果又提升社会可接受性。

cs.HC · cs.ET

查看原文摘要

Prior research has shown that providing feedback on group dynamics can improve the quality of small-group conversations. However, publicly delivered feedback that targets specific individuals may reduce social acceptability due to negative experiences such as social pressure, embarrassment, and resistance. This work investigates how public feedback can be designed to remain socially acceptable while maintaining its effectiveness in XR-based small-group conversations. Informed by social science and HCI literature, we identified three design strategies (incorporate humor, reduce social attention, and use indirectness) and proposed a set of metaphor- and agent-based 3D feedback probes. We then conducted a two-phase study: (1) an online survey with 50 participants to examine how such feedback designs are perceived under public and private delivery, and (2) follow-up interviews with 14 participants who completed the survey to better understand their interpretations and elicit additional insights. Results show that metaphor- and agent-based feedback can reduce social discomfort while maintaining effectiveness. Interview findings further highlighted the role of three strategies in making feedback easier to accept, while requiring careful balance. We also discussed design implications for creating socially acceptable 3D feedback to support inclusive small-group conversations in XR.

新论文 · v1arXiv:2611.17013

DiffSSMEye:基于结构化状态空间扩散的条件高频眼动合成

DiffSSMEye: Conditional High-Frequency Eye Movement Synthesis with Structured State-Space Diffusion

Kamrul Hasan, Mehedi Hasan Raju, Oleg V. Komogortsev

AI 速读 基于摘要

提出一种以S4层为骨干的条件去噪扩散模型,按用户身份与任务合成1,000 Hz高频注视速度序列。

cs.HC

查看原文摘要

Synthesizing high-frequency eye movements requires preserving long-range temporal dependencies and subject-specific oculomotor dynamics. However, methods based on generative adversarial networks (GANs) and variational autoencoders (VAEs) can struggle to preserve these characteristics simultaneously. We introduce DiffSSMEye, a conditional denoising diffusion probabilistic model with bidirectional Structured State Space Sequence (S4) layers for generating five-second gaze-velocity sequences at 1,000 Hz. Generation is conditioned on a coarse gaze reference, user identity, and task, where identity and task embeddings are incorporated through feature-wise linear modulation. Identity-preservation, multi-resolution spectral, and integrated-drift losses complement noise prediction to constrain biometric consistency, frequency structure, and displacement error. Subject-disjoint evaluation on GazeBase across seven tasks yields mean real--synthetic embedding cosine similarities of 0.91--0.95. DiffSSMEye also achieves the lowest median spatial errors among these baselines for horizontal and random saccade tasks. These results demonstrate improved spatial accuracy and biometric feature consistency for subject-specific gaze synthesis.