28 citations · 89 across the 29 of their papers we have counts for
31 papers
Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
Jiho Lee, Jeongeun Park, Heayoun Choi +2
Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by leveraging rich representations from pretrained vision-language models. However, the…
Moral Missions: Sustaining Responsible Practice by Surfacing Practitioner Moral Decision-Making Procedures
Teanna Barrett, B. Biira, Jainaba Jawara +8
A growing ecosystem of techniques, toolkits, and guidelines has been developed to help data scientists consider the social implications of data-driven technologies. However, prior…
Hedwig: Dynamic Autonomy for Coding Agents Under Local Oversight
Tanjal Shukla, K. J. Kevin Feng, Leijie Wang +2
Despite coding agents' advances in handling increasingly complex tasks, their continued tendency to introduce unintended edits, subtle bugs, and scope drift that slip past code rev…
Are Language Models Sensitive to Morally Irrelevant Distractors?
Andrew Shaw, Christina Hahn, Catherine Rasgaitis +5
With the rapid uptake of large language models (LLMs) across high-stakes settings, it is becoming increasingly important to ensure that LLMs behave in ways that align with human va…
On the Regulatory Potential of User Interfaces for AI Agent Governance
K. J. Kevin Feng, Tae Soo Kim, Rock Yuren Pang +3
AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Pri…
A Human Behavioral Baseline for Collective Governance in Software Projects
Mobina Noori, Mahasweta Chakraborti, Amy X Zhang +1
We study how open source communities describe participation and control through version controlled governance documents. Using a corpus of 710 projects with paired snapshots, we pa…
Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocations
Tzu-Sheng Kuo, Sophia Liu, Quan Ze Chen +4
AI agents, or bots, serve important roles in online communities. However, they are often designed by outsiders or a few tech-savvy members, leading to bots that may not align with…
PolicyPad: Collaborative Prototyping of LLM Policies
K. J. Kevin Feng, Tzu-Sheng Kuo, Quan Ze Chen +3
As LLMs gain adoption in high-stakes domains like mental health, domain experts are increasingly consulted to provide input into policies governing their behavior. From an observat…
Patterns in the Transition From Founder-Leadership to Community Governance of Open Source
Mobina Noori, Mahasweta Chakraborti, Amy X Zhang +1
Open digital public infrastructure needs community management to ensure accountability, sustainability, and robustness. Yet open-source projects often rely on centralized decision-…
Levels of Autonomy for AI Agents
K. J. Kevin Feng, David W. McDonald, Amy X. Zhang
Autonomy is a double-edged sword for AI agents, simultaneously unlocking transformative possibilities and serious risks. How can agent developers calibrate the appropriate levels o…
Penalizing Transparency? How AI Disclosure and Author Demographics Shape Human and AI Judgments About Writing
Inyoung Cheong, Alicia Guo, Mina Lee +7
As AI integrates in various types of human writing, calls for transparency around AI assistance are growing. However, if transparency operates on uneven ground and certain identity…
From Inquisitorial to Adversarial: Using Legal Theory to Redesign Online Reporting Systems
Leijie Wang, Weizi Wu, Lirong Que +2
User reporting systems play a central role in how online communities address interpersonal conflict and harassment, especially in private spaces such as direct messages, voice chat…
Seeing the Politics of Decentralized Social Media Protocols
Tolulope Oshinowo, Sohyeon Hwang, Amy X. Zhang +1
Calls to decentralize feed-based social media have been driven by concerns about the concentrated power of centralized platforms and their societal impact. In response, numerous de…
Facets, Taxonomies, and Syntheses: Navigating Structured Representations in LLM-Assisted Literature Review
Raymond Fok, Joseph Chee Chang, Marissa Radensky +4
Comprehensive literature review requires synthesizing vast amounts of research -- a labor intensive and cognitively demanding process. Most prior work focuses either on helping res…
Building Proactive and Instant-Reactive Safety Designs to Address Harassment in Social Virtual Reality
Zhehui Liao, Hanwen Zhao, Ayush Kulkarni +2
Social Virtual Reality (VR) games offer immersive socialization experiences but pose significant challenges of harassment. Common solutions, such as reporting and moderation, addre…
"It's Great Because It's Ran By Us": Empowering Teen Volunteer Discord Moderators to Design Healthy and Engaging Youth-Led Online Communities
Jina Yoon, Amy X. Zhang, Joseph Seering
Online communities can offer many benefits for youth including peer learning, cultural expression, and skill development. However, most HCI research on youth-focused online communi…
African Data Ethics: A Discursive Framework for Black Decolonial Data Science
Teanna Barrett, Chinasa T. Okolo, B. Biira +3
The shift towards pluralism in global data ethics acknowledges the importance of including perspectives from the Global Majority to develop responsible data science practices that…
Agonistic Image Generation: Unsettling the Hegemony of Intention
Andrew Shaw, Andre Ye, Ranjay Krishna +1
Current image generation paradigms prioritize actualizing user intention - "see what you intend" - but often neglect the sociopolitical dimensions of this process. However, it is i…
SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment
Quan Ze Chen, K. J. Kevin Feng, Chan Young Park +1
When different groups' values differ, one approach to model alignment is to steer models at inference time towards each group's preferences. However, techniques like in-context lea…
The Collaborative Practices and Motivations of Online Communities Dedicated to Voluntary Misinformation Response
Jina Yoon, Shreya Sathyanarayanan, Franziska Roesner +1
Responding to misinformation online can be an exhausting and thankless task. It takes time and energy to write effective content, puts users at risk of online harassment, and strai…
Chain of Alignment: Integrating Public Will with Expert Intelligence for Language Model Alignment
Andrew Konya, Aviv Ovadya, Kevin Feng +4
We introduce a method to measure the alignment between public will and language model (LM) behavior that can be applied to fine-tuning, online oversight, and pre-release safety che…
Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work
Aviv Ovadya, Kyle Redman, Luke Thorburn +11
This position paper argues that effectively "democratizing AI" requires democratic governance and alignment of AI, and that this is particularly valuable for decisions with systemi…
From Pen to Prompt: How Creative Writers Integrate AI into their Writing Practice
Alicia Guo, Shreya Sathyanarayanan, Leijie Wang +2
Creative writing is a deeply human craft, yet AI systems using large language models (LLMs) offer the automation of significant parts of the writing process. So why do some creativ…
Social-RAG: Retrieving from Group Interactions to Socially Ground AI Generation
Ruotong Wang, Xinyi Zhou, Lin Qiu +3
AI agents are increasingly tasked with making proactive suggestions in online spaces where groups collaborate, yet risk being unhelpful or even annoying if they fail to match group…