Quan Ze Chen

Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocations 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 the broader communit...

💜 This is a collaborative work with a wonderful team: @tskuo.bsky.social, Sophia Liu, @cqz.bsky.social, @josephseering.bsky.social, @axz.bsky.social, @haiyizhu.bsky.social, @kenholstein.bsky.social

📜 Check our paper for more details: www.arxiv.org/abs/2509.25492

Agonistic Image Generation: Unsettling the Hegemony of Intention Current image generation paradigms prioritize actualizing user intention - "see what you intend" - but often neglect the sociopolitical dimensions of this process. However, it is increasingly evident ...

This upcoming #FAccT2025 paper was w/ an amazing duo of undergrads @andreiskiii.bsky.social @andrewshawuw.bsky.social & deeply fuses philosophy with human-AI interaction design. "Unsettling the hegemony of intention" indeed! 😛 It also won the undergrad thesis award at UW 🏅 arxiv.org/abs/2502.15242

Can LLM prompting help social media users create and iterate on their content filters more easily?

In our #CHI2025 paper, we compared in an experiment three authoring strategies:
🤖 Prompting LLM
🔎 Labeling examples for ML classifiers
📐 Authoring keyword rules

(🧵1/N)

SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment 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 learning only consider ...

Check out our preprint here: arxiv.org/abs/2411.10912
This paper was a collaborative effort from our wonderful team ❤️ @kjfeng.me @chanpark.bsky.social @axz.bsky.social

With SPICA, we show the need to not only capture preferences, but also recognize and prioritize norms when it comes to in-context pluralistic alignment.

(8/9)

But, more importantly, groups that are often less well represented in alignment datasets see the biggest improvements.

(7/9)

Through human evaluations, we find that SPICA-aligned outputs are preferred more on average…

(6/9)

We then make use of these metrics during the retrieval process, producing pluralistically aligned examples that both reflect group preferences, and also their norms.

(5/9)

In SPICA, we sample **individual preferences** of members in a group to create metrics inspired by social norm theory that inform us of how each group prioritizes which examples they care more about (best illustrates group norms)

(4/9)

We argue that group level differences extend beyond their preferences for how to answer, and that different groups can also have preferences around which queries are better examples of how they prioritize their values.

(3/9)

Traditional in-context alignment (ICA) retrieves demonstration examples (query & answer) by finding those most similar to a new query. However, when there is a plurality of groups to align to, the same queries get picked regardless of group.

(2/9)

Screenshot of the first page of the paper SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment

In-context learning can be an effective way to conduct value alignment of LLMs through examples, but when there are multiple pluralistic groups, are the best examples for one group also the ones for another?

We explore this in our paper 🌟SPICA🌟
(🧵1/9)

ACM CHI 2025 PolicyCraft: Supporting Collaborative and Participatory Policy Design through Case-Grounded Deliberation Tzu-Sheng Kuo, Quan Ze Chen, Amy X. Zhang, Jane Hsieh, Haiyi Zhu, Kenneth Holstein

How can we help communities collaboratively shape policies that impact them?

In our #CHI2025 paper, we present PolicyCraft, a system that supports ✨collaborative policy design✨ through case-grounded deliberation.

(🧵/11)

Jim at the podium next to a slide about his research with an audience in front

Next @cqz.bsky.social gave a talk on Wed on targeted interventions to reduce uncertainty in judgments. Paper here: dl.acm.org/doi/10.1145/... He also discussed how it fits into his broader research trajectory and agenda, as he's headed onto the job market this year!

Interested in pursuing a Ph.D. at the intersection of computing, cultural heritage, and the digital humanities? I am recruiting Ph.D. students to join the Lab for Computing Cultural Heritage in the University of Washington's Information School! More information here: bcglee.com/lcch.html

Our lab has three paper talks at CSCW! But I want to highlight this one because @cqz.bsky.social is on the job market this year!! He works in crowdsourcing and human-AI systems. Make sure to check out his presentation on Wednesday. arxiv.org/abs/2305.01615

Don't forget to apply by *Oct 15* for AI2 research internships!

Interested in language models of science, evaluating AI-generated text, challenging retrieval settings, and human-AI collaborative reading/writing?

Come work with meeee! 😸

Learn more: kyleclo.github.io/mentorship