All

Papers

Browse and search HCI research papers from All

Active Filters

Institution: Independent researcher

353 results

Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces

The reasoning capabilities of Large Language Models (LLMs) have led to their increasing employment in several critical applications, particularly education, where they support problem-solving, tutoring, and personalized study. While there are a plethora of works showing the effectiveness of LLMs in generating step-by-…

Runtao Zhou et al.University of Virginia

Design Considerations for Human Oversight of AI: Insights from Co-Design Workshops and Work Design Theory

As AI systems become increasingly capable and autonomous, domain experts’ roles are shifting from performing tasks themselves to overseeing AI-generated outputs. Such oversight is critical, as undetected errors can have serious consequences or undermine the benefits of AI. Effective oversight, however, depends not onl…

Cedric Faas et al.Saarland University

Mental Models in Human-AI Interaction: Systematic Review of Empirical Methodologies and Guidelines

The notion of mental model has long been used in HCI to capture people's understanding and reasoning about computing systems. Eliciting users' mental models can explain their behaviors and attitudes toward a system—why and how they use, rely on, trust, or reject it. However, its use remains conceptually fragmented and…

Téo Sanchez et al.Paris-Saclay University

No Code, No Cloud: On-Device Mockup-to-Code with Lightweight Vision-Language AI

Bridging the gap between visual design and functional code remains a persistent challenge in modern UI workflows, especially for small teams and non-programmers. Existing solutions, such as Figma-to-code tools and recent vision language models (VLMs), often depend on proprietary cloud APIs or large-scale architectures…

Abinas Kuganathan et al.Independent Researcher

AdRecommended

Learn AI Coding at CodeNow

Structured lessons, hands-on projects, and continuous updates for people bringing AI into real development work.

Explore Now

When Help Hurts: Verification Load and Fatigue with AI Coding Assistants

AI coding assistants help, but developers still spend effort verifying model output. We isolate interface effects by holding a single LLM fixed while N=60 participants solve three Python tasks with Inline, Chat, or Structured prompting, plus a no-AI control. AI reduced workload by -18.2 TLX points and time by 22% (25.…

Guangrui Fan et al.Taiyuan University of Science and Technology

Take the Power Back: Screen-Based Personal Moderation Against Hate Speech on Instagram

Hate speech remains a pressing challenge on social media, where platform moderation often fails to protect targeted users. Personal moderation tools that let users decide how content is filtered can address some of these shortcomings. However, it remains an open question on which screens (e.g., the comments, the reels…

Anna Ricarda Luther et al.Telecooperation Lab

Play/Destroy: A portfolio of sound destruction devices

Digital media operates on a curious boundary between storage and loss. While each new storage format promises a permanent solution to our exponentially expanding media libraries, they inevitably fail or otherwise become unusable. This paper reflects on a long-term design process that attempts to bring a different para…

Yann Seznec et al.KTH Royal Institute of Technology

FlueBricks: A Construction Kit of Flute-like Instruments for Acoustic Reasoning

We present FlueBricks, a construction kit for acoustic reasoning via building and customizing flute-like instruments. By assembling generator, resonator, and connector modules that embody various aeroacoustic properties, users gain deeper understanding of how blowhole, tube length, and tone-hole placement alter onset,…

Bo-Yu Chen et al.National Taiwan University

Privy: Envisioning and Mitigating Privacy Risks for Consumer-facing AI Product Concepts

AI creates and exacerbates privacy risks, yet practitioners lack effective resources to identify and mitigate these risks. We present Privy, a tool that guides practitioners without privacy expertise through structured privacy impact assessments to: (i) identify relevant risks in novel AI product concepts, and (ii) pr…

Hao-Ping (Hank) Lee et al.Carnegie Mellon University

Laughing Through the Struggles: Understanding ADHD Experience and Community Engagement Through Memes and Comments on Instagram

While public discourse often reduces Attention-Deficit Hyperactivity Disorder (ADHD) to stereotypes that overlook the invisible struggles of those who live with it, ADHD people are increasingly using social media to express their experiences on their own terms. On platforms like Instagram, memes have become a powerful…

Fan Zhang et al.Independent Researcher

ViRAS: Design Artifacts to Explore Socio-Material Configurations through a Research-through-Design Approach in Robot-Assisted Surgery

Robot-assisted surgery (RAS) has raised concerns within human-computer interaction, particularly regarding the socio-material configurations of robotic systems and their impact on surgical practices. To investigate these configurations in the context of the da Vinci robotic system, we used a research-through-design ap…

Peter Sörries et al.Free University of Berlin

SituFont: A Just-in-Time Adaptive Intervention Interface for Enhancing Mobile Readability in Situational Visual Impairments

Situational visual impairments (SVIs) hinder mobile readability, causing discomfort and limiting information access. Building on prior work in adaptive typography and accessibility, this paper presents SituFont, a context-aware and human-in-the-loop adaptive typography adjustment approach that enhances smartphone mobi…

Jingruo Chen et al.Cornell University

Giving Meaning to Movements: Challenges and Opportunities in Expanding Communication by Pairing Unaided AAC with Speech Generated Messages

Augmentative and Alternative Communication (AAC) technologies are categorized into two forms: aided AAC, which uses external devices like speech-generating systems to produce standardized output, and unaided AAC, which relies on body-based gestures for natural expression but requires shared understanding. We investiga…

Imran Kabir et al.Pennsylvania State University

A Cantilevered DeltaXY Positioning Mechanism Enabling Rackable Digital Fabrication Form Factors

Desktop digital fabrication presumes form-factors designed for workbenches, limiting suitability for other spaces and workflows. We propose a class of physically narrow and deep “rackable” digital fabrication machines that offers opportunities for new applications and interactions. Flexible and inconspicuous placement…

Ilan E Moyer et al.Massachusetts Institute of Technology

TableTale: Reviving the Narrative Interplay Between Tables and Text in Scientific Papers

Data tables play a central role in scientific papers. However, their meaning is often co-constructed with surrounding text through narrative interplay, making comprehension cognitively demanding for readers. In this work, we explore how interfaces can better support this reading process. We conducted a formative study…

Liangwei Wang et al.Hong Kong University of Science and Technology

No Spirituality Please, We’re HCI: Challenges for HCI Research on Religion and Spirituality

Religion and spirituality (R/S) shape billions of lives, yet they remain marginal in Human–Computer Interaction (HCI) research. Prior literature reviews mapped fragments of this space but missed key contributions and the lived realities of its researchers. We extend this picture through a review of 206 ACM and IEEE pu…

Sara Wolf et al.Julius Maximilian University of Wurzburg

Engaging Communities Meaningfully in Defining Disability Representation for AI Image Generation

Media representations of people with disabilities profoundly influence societal perceptions, yet have historically been absent, stereotyped, or inaccurate. As AI-generated visual media becomes increasingly prevalent, there is a critical opportunity to address these misrepresentations. Responding to the lack of collect…

Anja Thieme et al.Microsoft

Beyond Content Exposure: Systemic Factors Driving Moderators' Mental Health Crisis in Africa

Content moderators review disturbing content to protect social media users, often at significant cost to their mental health. Recent reports document the mental health conditions of African moderators as notably problematic. Beyond the content itself, what factors contribute to the deteriorating mental health of these…

Nuredin Ali et al.University of Minnesota

My Favorite Streamer is an LLM: Discovering, Bonding, and Co-Creating in AI VTuber Fandom

AI VTubers, where the performer is not human but algorithmically generated, introduce a new context for fandom. While human VTubers have been substantially studied for their cultural appeal, parasocial dynamics, and community economies, little is known about how audiences engage with their AI counterparts. To address…

Jiayi Ye et al.Independent Researcher

From Vulnerable to Resilient: Examining Parent and Teen Perceptions on How to Respond to Unwanted Cybergrooming Advances

Cybergrooming is a form of online abuse that threatens teens' mental health and physical safety. Yet, most prior work has focused on detecting perpetrators’ behaviors, leaving a limited understanding of how teens might respond to such unwanted advances. To address this gap, we conducted an online survey with 74 partic…

Xinyi Zhang et al.Virginia Tech

Paper Title	Authors	Research Topics	Paper Database	Year
Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces The reasoning capabilities of Large Language Models (LLMs) have led to their increasing employment in several critical applications, particularly education, where they support problem-solving, tutoring, and personalized study. While there are a plethora of works showing the effectiveness of LLMs in generating step-by-…	RZ Runtao Zhou et al.University of Virginia
Design Considerations for Human Oversight of AI: Insights from Co-Design Workshops and Work Design Theory As AI systems become increasingly capable and autonomous, domain experts’ roles are shifting from performing tasks themselves to overseeing AI-generated outputs. Such oversight is critical, as undetected errors can have serious consequences or undermine the benefits of AI. Effective oversight, however, depends not onl…	CF Cedric Faas et al.Saarland University
Mental Models in Human-AI Interaction: Systematic Review of Empirical Methodologies and Guidelines The notion of mental model has long been used in HCI to capture people's understanding and reasoning about computing systems. Eliciting users' mental models can explain their behaviors and attitudes toward a system—why and how they use, rely on, trust, or reject it. However, its use remains conceptually fragmented and…	TS Téo Sanchez et al.Paris-Saclay University
No Code, No Cloud: On-Device Mockup-to-Code with Lightweight Vision-Language AI Bridging the gap between visual design and functional code remains a persistent challenge in modern UI workflows, especially for small teams and non-programmers. Existing solutions, such as Figma-to-code tools and recent vision language models (VLMs), often depend on proprietary cloud APIs or large-scale architectures…	AK Abinas Kuganathan et al.Independent Researcher
AdRecommended Learn AI Coding at CodeNow Structured lessons, hands-on projects, and continuous updates for people bringing AI into real development work. Explore Now
emoji_events When Help Hurts: Verification Load and Fatigue with AI Coding Assistants AI coding assistants help, but developers still spend effort verifying model output. We isolate interface effects by holding a single LLM fixed while N=60 participants solve three Python tasks with Inline, Chat, or Structured prompting, plus a no-AI control. AI reduced workload by -18.2 TLX points and time by 22% (25.…	GF Guangrui Fan et al.Taiyuan University of Science and Technology
Take the Power Back: Screen-Based Personal Moderation Against Hate Speech on Instagram Hate speech remains a pressing challenge on social media, where platform moderation often fails to protect targeted users. Personal moderation tools that let users decide how content is filtered can address some of these shortcomings. However, it remains an open question on which screens (e.g., the comments, the reels…	AL Anna Ricarda Luther et al.Telecooperation Lab
Play/Destroy: A portfolio of sound destruction devices Digital media operates on a curious boundary between storage and loss. While each new storage format promises a permanent solution to our exponentially expanding media libraries, they inevitably fail or otherwise become unusable. This paper reflects on a long-term design process that attempts to bring a different para…	YS Yann Seznec et al.KTH Royal Institute of Technology
FlueBricks: A Construction Kit of Flute-like Instruments for Acoustic Reasoning We present FlueBricks, a construction kit for acoustic reasoning via building and customizing flute-like instruments. By assembling generator, resonator, and connector modules that embody various aeroacoustic properties, users gain deeper understanding of how blowhole, tube length, and tone-hole placement alter onset,…	BC Bo-Yu Chen et al.National Taiwan University
emoji_events Privy: Envisioning and Mitigating Privacy Risks for Consumer-facing AI Product Concepts AI creates and exacerbates privacy risks, yet practitioners lack effective resources to identify and mitigate these risks. We present Privy, a tool that guides practitioners without privacy expertise through structured privacy impact assessments to: (i) identify relevant risks in novel AI product concepts, and (ii) pr…	HL Hao-Ping (Hank) Lee et al.Carnegie Mellon University
emoji_events Laughing Through the Struggles: Understanding ADHD Experience and Community Engagement Through Memes and Comments on Instagram While public discourse often reduces Attention-Deficit Hyperactivity Disorder (ADHD) to stereotypes that overlook the invisible struggles of those who live with it, ADHD people are increasingly using social media to express their experiences on their own terms. On platforms like Instagram, memes have become a powerful…	FZ Fan Zhang et al.Independent Researcher
ViRAS: Design Artifacts to Explore Socio-Material Configurations through a Research-through-Design Approach in Robot-Assisted Surgery Robot-assisted surgery (RAS) has raised concerns within human-computer interaction, particularly regarding the socio-material configurations of robotic systems and their impact on surgical practices. To investigate these configurations in the context of the da Vinci robotic system, we used a research-through-design ap…	PS Peter Sörries et al.Free University of Berlin
SituFont: A Just-in-Time Adaptive Intervention Interface for Enhancing Mobile Readability in Situational Visual Impairments Situational visual impairments (SVIs) hinder mobile readability, causing discomfort and limiting information access. Building on prior work in adaptive typography and accessibility, this paper presents SituFont, a context-aware and human-in-the-loop adaptive typography adjustment approach that enhances smartphone mobi…	JC Jingruo Chen et al.Cornell University
Giving Meaning to Movements: Challenges and Opportunities in Expanding Communication by Pairing Unaided AAC with Speech Generated Messages Augmentative and Alternative Communication (AAC) technologies are categorized into two forms: aided AAC, which uses external devices like speech-generating systems to produce standardized output, and unaided AAC, which relies on body-based gestures for natural expression but requires shared understanding. We investiga…	IK Imran Kabir et al.Pennsylvania State University
emoji_events A Cantilevered DeltaXY Positioning Mechanism Enabling Rackable Digital Fabrication Form Factors Desktop digital fabrication presumes form-factors designed for workbenches, limiting suitability for other spaces and workflows. We propose a class of physically narrow and deep “rackable” digital fabrication machines that offers opportunities for new applications and interactions. Flexible and inconspicuous placement…	IM Ilan E Moyer et al.Massachusetts Institute of Technology
TableTale: Reviving the Narrative Interplay Between Tables and Text in Scientific Papers Data tables play a central role in scientific papers. However, their meaning is often co-constructed with surrounding text through narrative interplay, making comprehension cognitively demanding for readers. In this work, we explore how interfaces can better support this reading process. We conducted a formative study…	LW Liangwei Wang et al.Hong Kong University of Science and Technology
No Spirituality Please, We’re HCI: Challenges for HCI Research on Religion and Spirituality Religion and spirituality (R/S) shape billions of lives, yet they remain marginal in Human–Computer Interaction (HCI) research. Prior literature reviews mapped fragments of this space but missed key contributions and the lived realities of its researchers. We extend this picture through a review of 206 ACM and IEEE pu…	SW Sara Wolf et al.Julius Maximilian University of Wurzburg
Engaging Communities Meaningfully in Defining Disability Representation for AI Image Generation Media representations of people with disabilities profoundly influence societal perceptions, yet have historically been absent, stereotyped, or inaccurate. As AI-generated visual media becomes increasingly prevalent, there is a critical opportunity to address these misrepresentations. Responding to the lack of collect…	AT Anja Thieme et al.Microsoft
Beyond Content Exposure: Systemic Factors Driving Moderators' Mental Health Crisis in Africa Content moderators review disturbing content to protect social media users, often at significant cost to their mental health. Recent reports document the mental health conditions of African moderators as notably problematic. Beyond the content itself, what factors contribute to the deteriorating mental health of these…	NA Nuredin Ali et al.University of Minnesota
emoji_events My Favorite Streamer is an LLM: Discovering, Bonding, and Co-Creating in AI VTuber Fandom AI VTubers, where the performer is not human but algorithmically generated, introduce a new context for fandom. While human VTubers have been substantially studied for their cultural appeal, parasocial dynamics, and community economies, little is known about how audiences engage with their AI counterparts. To address…	JY Jiayi Ye et al.Independent Researcher
From Vulnerable to Resilient: Examining Parent and Teen Perceptions on How to Respond to Unwanted Cybergrooming Advances Cybergrooming is a form of online abuse that threatens teens' mental health and physical safety. Yet, most prior work has focused on detecting perpetrators’ behaviors, leaving a limited understanding of how teens might respond to such unwanted advances. To address this gap, we conducted an online survey with 74 partic…	XZ Xinyi Zhang et al.Virginia Tech