Quan Ze Chen

Quan Ze Chen

@cqz.name

124 followers37 following9 posts

Quan Ze Chen reposted

Tzu-Sheng Kuo 郭子生
@tskuo.bsky.social

Replying to @tskuo.bsky.social

💜 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

arxiv.orgBotender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based ProvocationsAI 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...

Quan Ze Chen reposted

Amy Zhang
@axz.bsky.social

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

arxiv.orgAgonistic Image Generation: Unsettling the Hegemony of IntentionCurrent 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 ...

Quan Ze Chen reposted

Leijie Wang
@leijiew.bsky.social

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)

Quan Ze Chen
@cqz.name

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)

View full thread
Quan Ze Chen
@cqz.name

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)

Quan Ze Chen
@cqz.name

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)

View full thread
Quan Ze Chen
@cqz.name

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)

View full thread
Quan Ze Chen
@cqz.name

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)

Quan Ze Chen
@cqz.name

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)

Quan Ze Chen
@cqz.name

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)

Quan Ze Chen
@cqz.name

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)

Quan Ze Chen
@cqz.name

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)

Quan Ze Chen reposted

Tzu-Sheng Kuo 郭子生
@tskuo.bsky.social

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)

Quan Ze Chen reposted

Amy Zhang
@axz.bsky.social

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

arxiv.orgJudgment Sieve: Reducing Uncertainty in Group Judgments through...When groups of people are tasked with making a judgment, the issue of uncertainty often arises. Existing methods to reduce uncertainty typically focus on iteratively improving specificity in the...
Amy Zhang@axz.bsky.social

Excited to head to CSCW ‘23 later today! I’m only going to be there Monday bc of teaching so I plan to just hang out somewhere in the open spaces to meet ppl, come say hi :)

You are up to date.