Ziheng (Fred) Huang

I’m a 4th year Computer Science PhD Candidate at the University of Illinois at Urbana-Champaign advised by Professors Hari Sundaram and Tal August.

I’m broadly interested in AI for social good. I study how AI systems can broaden access to justice. I pursue this goal by (1) investigating how people use AI systems for access to justice, (2) creating novel interactions that augment people’s ability to gain access to justice, and (3) evaluating AI systems’ ability to broaden access to justice.

Before joining UIUC, I earned a Bachelor’s degree in Computer Engineering and a Bachelor’s degree in Neurobiology from University of California San Diego. I was fortunate to work with Professors Stephen MacNeil and Steven Dow on Transparent and Controllable AI memory management, Design Thinking, and Education.

selected publications

Living Contracts: Beyond Document-Centric Interaction with Legal Agreements

Ziheng Huang, Robin Kar, Hari Sundaram, and Tal August

In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, , 2026

Abs DOI

User interaction with legal contracts has been limited to document reading, which is often complicated by complex, ambiguous legal language. We explore possible futures where contract interfaces go beyond single document interfaces to (1) educate users with legal rights not stated in the contract, (2) transform legal language into alternative representations to aid information tasks before, during, and after signing, and (3) proactively supply contractual information at relevant moments. We refer to these future interfaces collectively as Living Contracts. Using residential leases as a case study, we created three design probes representing different possible Living Contracts. A three-part qualitative study (N=18) revealed participants’ barriers to interacting with contracts, including interpreting complex language, uncertainty about legal rights, and the pressure to sign quickly. Participants’ feedback on the probes highlighted how Living Contracts have the potential to address these challenges and open new design opportunities for human-contract interactions beyond document reading.
TermSight: Making Service Contracts Approachable

Ziheng Huang, Tal August, and Hari Sundaram

In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, , 2026

Abs DOI

Legal contracts govern much of our society, but their specialized language is difficult for non-experts to read. While AI has enabled simplification of complex language, legal contracts pose unique challenges because of their connection to readers’ values, ambiguity, and legally binding nature. Based on a formative study (N=20) using Terms of Service (ToS) as example contracts to study challenges in contract reading, we developed TermSight, an intelligent reading interface to probe the opportunities and challenges of designing augmentations for legal text. TermSight guides readers to relevant clauses with color-coded plain-language snippets of information and contextualizes ambiguous language with definitions and hypothetical scenarios. Importantly, TermSight’s features always foreground the original, legally-binding contract text (e.g., linking to associated clauses). Our within-subjects study (N=20) demonstrated the opportunities of TermSight in making ToS significantly easier to read and navigate while revealing the challenges of augmenting service contracts such as ToS.
Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agents

Ziheng Huang, Sebastian Gutierrez, Hemanth Kamana, and Stephen Macneil

In Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, San Francisco, CA, USA, 2023

Abs DOI

The recent advent of large language models (LLM) has resulted in high-performing conversational agents such as ChatGPT. These agents must remember key information from an ongoing conversation to provide responses that are contextually relevant to the user. However, these agents have limited memory and can be distracted by irrelevant parts of the conversation. While many strategies exist to manage conversational memory, users currently lack affordances for viewing and controlling what the agent remembers, resulting in a poor mental model and conversational breakdowns. In this paper, we present Memory Sandbox, an interactive system and design probe that allows users to manage the conversational memory of LLM-powered agents. By treating memories as data objects that can be viewed, manipulated, recorded, summarized, and shared across conversations, Memory Sandbox provides interaction affordances for users to manage how the agent should ‘see’ the conversation.