arXiv subjects

Leijie Wang

Publications and source records attributed to Leijie Wang.

17 recordsLinked to original sources

arXiv2026

Middleware for Feed Recommendation in Practice: How Feed Creators Build, Maintain, and Sustain Custom Feeds on Bluesky

Scholars have long proposed third-party middleware as an alternative to centralized algorithmic feeds: feeds built and distributed by independent feed creators. This vision saw no large-scale instantiation until Bluesky, a decentralized microblogging platform, introduced custom feeds in 2023. Although central to the middleware ecosystem, we know little about how feed creators understand their role, build feeds, and sustain them. Through interviews with n = 26 feed creators and third-party developers of feed-building tools, and analysis of n = 88,302 custom feeds, we identify two creator orientations---utility-providing and community-building. Additionally, creators struggle to maintain feeds that fully realize middleware ideals: they lack granular interaction data, receive little feedback, and lack technical expertise to act on either. Finally, creators sustain their feeds as unpaid hobbyists with little platform support and are divided on whether to monetize beyond covering costs. We conclude with design and policy implications for strengthening the middleware feed ecosystem.

cs.HC↗

arXiv2026

Compass: Continuously Aligning Social Media Feeds via In-Situ Reflections

Social media recommendation feeds often optimize for users' immediate impulses rather than preferences they would hold after deeper reflection. Some systems address this misalignment by incorporating users' explicit preferences via a configuration page or in-feed controls instead of just behavioral signals. However, users typically have evolving preferences, and their stated preferences and behavior naturally diverge, necessitating continuous reflection and feed realignment. But existing strategies require the user to take initiative and are often effortful; as a result, in practice they are rarely invoked. We present Compass, a system that aligns a user's feed with their reflective preferences by helping users reflect on and articulate their preferences given their behavior. To enable continuous reflection during everyday browsing, Compass surfaces in-situ reflections via lightweight notifications, while feed alignment is achieved by periodically simulating behavioral signals and directly manipulating feed content. We embedded Compass within YouTube Shorts and compared it against a baseline without continuous support through a 10-day field study (N=15). We found that Compass promoted more reflective and purposeful feed consumption, iterative preference adjustment, and stronger feed alignment, without sacrificing the casual nature of feed browsing.

cs.HC↗

arXiv2026

From Inquisitorial to Adversarial: Using Legal Theory to Redesign Online Reporting Systems

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 chats, and end-to-end encrypted messaging. These settings complicate evidence collection for community moderators while heightening users' concerns about procedural justice and privacy. To examine these challenges, we draw on adversarial legal frameworks from offline judicial systems and apply them to community-level reporting systems, using Discord as a research site. We find that online community reporting systems often follow an inquisitorial model, in which moderators lead evidence collection and case development, rather than an adversarial model, which gives users greater control over how evidence is presented and contested. Although adversarial practices can strengthen procedural justice and protect privacy, they can also introduce new risks of abuse, underscoring the need for careful threat modeling. Building on this analysis, we present a design space for giving users greater control over the disclosure and authentication of evidence while accounting for the privacy constraints and technical affordances of online communities. We conclude by discussing how this design space can inform platform-level reporting systems and how cryptographic techniques may help reinforce these systems amid growing distrust in platforms.

cs.HC↗

arXiv2026

Hedwig: Dynamic Autonomy for Coding Agents Under Local Oversight

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 review means developers must still decide how much autonomy to grant them. However, existing approaches for setting an agent's level of autonomy, such as static permission settings or instruction files, cannot account for how developers' preferences for agent autonomy can shift across tasks and over time. We conducted a formative survey with 21 software engineers who use coding agents and found that they experience frustration with calibrating autonomy and have evolving preferences for level of oversight. Building on these insights, we present Hedwig, a CLI coding agent that dynamically adjusts its autonomy level based on developer-agent interactions across sessions. Rather than operating on a global, fixed autonomy configuration, Hedwig learns an evolving set of behavioral guidelines from developer decisions and feedback, reducing friction on work for which the agent has earned trust, while tightening oversight when the agent operates outside familiar territory. Hedwig demonstrates the potential of a new paradigm where agents intelligently adapt their level of autonomy based on user trust through active, longitudinal collaboration.

cs.HC↗

arXiv2026

Agile Deliberation: Concept Deliberation for Subjective Visual Classification

From content moderation to content curation, applications requiring vision classifiers for visual concepts are rapidly expanding. Existing human-in-the-loop approaches typically assume users begin with a clear, stable concept understanding to be able to provide high-quality supervision. In reality, users often start with a vague idea and must iteratively refine it through "concept deliberation", a practice we uncovered through structured interviews with content moderation experts. We operationalize the common strategies in deliberation used by real content moderators into a human-in-the-loop framework called "Agile Deliberation" that explicitly supports evolving and subjective concepts. The system supports users in defining the concept for themselves by exposing them to borderline cases. The system does this with two deliberation stages: (1) concept scoping, which decomposes the initial concept into a structured hierarchy of sub-concepts, and (2) concept iteration, which surfaces semantically borderline examples for user reflection and feedback to iteratively align an image classifier with the user's evolving intent. Since concept deliberation is inherently subjective and interactive, we painstakingly evaluate the framework through 18 user sessions, each 1.5h long, rather than standard benchmarking datasets. We find that Agile Deliberation achieves 7.5% higher F1 scores than automated decomposition baselines and more than 3% higher than manual deliberation, while participants reported clearer conceptual understanding and lower cognitive effort.

cs.AI↗

arXiv2025

Promptimizer: User-Led Prompt Optimization for Personal Content Classification

While LLMs now enable users to create content classifiers easily through natural language, automatic prompt optimization techniques are often necessary to create performant classifiers. However, such techniques can fail to consider how social media users want to evolve their filters over the course of usage, including desiring to steer them in different ways during initialization and iteration. We introduce a user-centered prompt optimization technique, Promptimizer, that maintains high performance and ease-of-use but additionally (1) allows for user input into the optimization process and (2) produces final prompts that are interpretable. A lab experiment (n=16) found that users significantly preferred Promptimizer's human-in-the-loop optimization over a fully automatic approach. We further implement Promptimizer into Puffin, a tool to support YouTube content creators in creating and maintaining personal classifiers to manage their comments. Over a 3-week deployment with 10 creators, participants successfully created diverse filters to better understand their audiences and protect their communities.

cs.HC↗

arXiv2025

From Pen to Prompt: How Creative Writers Integrate AI into their Writing Practice

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 creative writers choose to use AI? Through interviews and observed writing sessions with 18 creative writers who already use AI regularly in their writing practice, we find that creative writers are intentional about how they incorporate AI, making many deliberate decisions about when and how to engage AI based on their core values, such as authenticity and craftsmanship. We characterize the interplay between writers' values, their fluid relationships with AI, and specific integration strategies -- ultimately enabling writers to create new AI workflows without compromising their creative values. We provide insight for writing communities, AI developers and future researchers on the importance of supporting transparency of these emerging writing processes and rethinking what AI features can best serve writers.

cs.HC↗

arXiv2025

End User Authoring of Personalized Content Classifiers: Comparing Example Labeling, Rule Writing, and LLM Prompting

Existing tools for laypeople to create personal classifiers often assume a motivated user working uninterrupted in a single, lengthy session. However, users tend to engage with social media casually, with many short sessions on an ongoing, daily basis. To make creating personal classifiers for content curation easier for such users, tools should support rapid initialization and iterative refinement. In this work, we compare three strategies -- (1) example labeling, (2) rule writing, and (3) large language model (LLM) prompting -- for end users to build personal content classifiers. From an experiment with 37 non-programmers tasked with creating personalized moderation filters, we found that participants preferred different initializing strategies in different contexts, despite LLM prompting's better performance. However, all strategies faced challenges with iterative refinement. To overcome challenges in iterating on their prompts, participants even adopted hybrid approaches such as providing examples as in-context examples or writing rule-like prompts.

cs.HC↗

arXiv2024

Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies

Log data can reveal valuable information about how users interact with Web search services, what they want, and how satisfied they are. However, analyzing user intents in log data is not easy, especially for emerging forms of Web search such as AI-driven chat. To understand user intents from log data, we need a way to label them with meaningful categories that capture their diversity and dynamics. Existing methods rely on manual or machine-learned labeling, which are either expensive or inflexible for large and dynamic datasets. We propose a novel solution using large language models (LLMs), which can generate rich and relevant concepts, descriptions, and examples for user intents. However, using LLMs to generate a user intent taxonomy and apply it for log analysis can be problematic for two main reasons: (1) such a taxonomy is not externally validated; and (2) there may be an undesirable feedback loop. To address this, we propose a new methodology with human experts and assessors to verify the quality of the LLM-generated taxonomy. We also present an end-to-end pipeline that uses an LLM with human-in-the-loop to produce, refine, and apply labels for user intent analysis in log data. We demonstrate its effectiveness by uncovering new insights into user intents from search and chat logs from the Microsoft Bing commercial search engine. The proposed work's novelty stems from the method for generating purpose-driven user intent taxonomies with strong validation. This method not only helps remove methodological and practical bottlenecks from intent-focused research, but also provides a new framework for generating, validating, and applying other kinds of taxonomies in a scalable and adaptable way with reasonable human effort.

cs.IR↗

arXiv2024

Illuminating the Unseen: Investigating the Context-induced Harms in Behavioral Sensing

Behavioral sensing technologies are rapidly evolving across a range of well-being applications. Despite its potential, concerns about the responsible use of such technology are escalating. In response, recent research within the sensing technology has started to address these issues. While promising, they primarily focus on broad demographic categories and overlook more nuanced, context-specific identities. These approaches lack grounding within domain-specific harms that arise from deploying sensing technology in diverse social, environmental, and technological settings. Additionally, existing frameworks for evaluating harms are designed for a generic ML life cycle, and fail to adapt to the dynamic and longitudinal considerations for behavioral sensing technology. To address these gaps, we introduce a framework specifically designed for evaluating behavioral sensing technologies. This framework emphasizes a comprehensive understanding of context, particularly the situated identities of users and the deployment settings of the sensing technology. It also highlights the necessity for iterative harm mitigation and continuous maintenance to adapt to the evolving nature of technology and its use. We demonstrate the feasibility and generalizability of our framework through post-hoc evaluations on two real-world behavioral sensing studies conducted in different international contexts, involving varied population demographics and machine learning tasks. Our evaluations provide empirical evidence of both situated identity-based harm and more domain-specific harms, and discuss the trade-offs introduced by implementing bias mitigation techniques.

cs.HC↗

arXiv2024

The Use of Generative Search Engines for Knowledge Work and Complex Tasks

Until recently, search engines were the predominant method for people to access online information. The recent emergence of large language models (LLMs) has given machines new capabilities such as the ability to generate new digital artifacts like text, images, code etc., resulting in a new tool, a generative search engine, which combines the capabilities of LLMs with a traditional search engine. Through the empirical analysis of Bing Copilot (Bing Chat), one of the first publicly available generative search engines, we analyze the types and complexity of tasks that people use Bing Copilot for compared to Bing Search. Findings indicate that people use the generative search engine for more knowledge work tasks that are higher in cognitive complexity than were commonly done with a traditional search engine.

cs.IR↗

arXiv2024

Pika: Empowering Non-Programmers to Author Executable Governance Policies in Online Communities

Internet users have formed a wide array of online communities with nuanced and diverse community goals and norms. However, most online platforms only offer a limited set of governance models in their software infrastructure and leave little room for customization. Consequently, technical proficiency becomes a prerequisite for online communities to build governance policies in code, excluding non-programmers from participation in designing community governance. In this paper, we present Pika, a system that empowers non-programmers to author a wide range of executable governance policies. At its core, Pika incorporates a declarative language that decomposes governance policies into modular components, thereby facilitating expressive policy authoring through a user-friendly, form-based web interface. Our user studies with 17 participants show that Pika can empower non-programmers to author governance policies approximately 2.5 times faster than programmers who author in code. We also provide insights about Pika's expressivity in supporting diverse policies that online communities want.

cs.HC↗

arXiv2023

A Framework for Designing Fair Ubiquitous Computing Systems

Over the past few decades, ubiquitous sensors and systems have been an integral part of humans' everyday life. They augment human capabilities and provide personalized experiences across diverse contexts such as healthcare, education, and transportation. However, the widespread adoption of ubiquitous computing has also brought forth concerns regarding fairness and equitable treatment. As these systems can make automated decisions that impact individuals, it is essential to ensure that they do not perpetuate biases or discriminate against specific groups. While fairness in ubiquitous computing has been an acknowledged concern since the 1990s, it remains understudied within the field. To bridge this gap, we propose a framework that incorporates fairness considerations into system design, including prioritizing stakeholder perspectives, inclusive data collection, fairness-aware algorithms, appropriate evaluation criteria, enhancing human engagement while addressing privacy concerns, and interactive improvement and regular monitoring. Our framework aims to guide the development of fair and unbiased ubiquitous computing systems, ensuring equal treatment and positive societal impact.

cs.HC↗

arXiv2023

"Is Reporting Worth the Sacrifice of Revealing What I Have Sent?": Privacy Considerations When Reporting on End-to-End Encrypted Platforms

User reporting is an essential component of content moderation on many online platforms -- in particular, on end-to-end encrypted (E2EE) messaging platforms where platform operators cannot proactively inspect message contents. However, users' privacy concerns when considering reporting may impede the effectiveness of this strategy in regulating online harassment. In this paper, we conduct interviews with 16 users of E2EE platforms to understand users' mental models of how reporting works and their resultant privacy concerns and considerations surrounding reporting. We find that users expect platforms to store rich longitudinal reporting datasets, recognizing both their promise for better abuse mitigation and the privacy risk that platforms may exploit or fail to protect them. We also find that users have preconceptions about the respective capabilities and risks of moderators at the platform versus community level -- for instance, users trust platform moderators more to not abuse their power but think community moderators have more time to attend to reports. These considerations, along with perceived effectiveness of reporting and how to provide sufficient evidence while maintaining privacy, shape how users decide whether, to whom, and how much to report. We conclude with design implications for a more privacy-preserving reporting system on E2EE messaging platforms.

cs.HC↗

arXiv2019

Lusin and Suslin properties of function spaces

A topological space is $Suslin$ ($Lusin$) if it is a continuous (and bijective) image of a Polish space. For a Tychonoff space $X$ let $C_p(X)$, $C_k(X)$ and $C_{{\downarrow}F}(X)$ be the space of continuous real-valued functions on $X$, endowed with the topology of pointwise convergence, the compact-open topology, and the Fell hypograph topology, respectively. For a metrizable space $X$ we prove the equivalence of the following statements: (1) $X$ is $σ$-compact, (2) $C_p(X)$ is Suslin, (3) $C_k(X)$ is Suslin, (4) $C_{{\downarrow}F}(X)$ is Suslin, (5) $C_p(X)$ is Lusin, (6) $C_k(X)$ is Lusin, (7) $C_{{\downarrow}F}(X)$ is Lusin, (8) $C_p(X)$ is $F_σ$-Lusin, (9) $C_k(X)$ is $F_σ$-Lusin, (10) $C_{{\downarrow}F}(X)$ is $C_{δσ}$-Lusin. Also we construct an example of a sequential $\aleph_0$-space $X$ with a unique non-isolated point such that the function spaces $C_p(X)$, $C_k(X)$ and $C_{{\downarrow}F}(X)$ are not Suslin.

math.GN↗

arXiv2019

Baire category properties of function spaces with the Fell hypograph topology

For a Tychonoff space $X$ and a subspace $Y\subset\mathbb R$, we study Baire category properties of the space $C_{\downarrow F}(X,Y)$ of continuous functions from $X$ to $Y$, endowed with the Fell hypograph topology. We characterize pairs $X,Y$ for which the function space $C_{\downarrow F}(X,Y)$ is $\infty$-meager, meager, Baire, Choquet, strong Choquet, (almost) complete-metrizable or (almost) Polish.

math.GN↗

arXiv2019

On Baire category properties of function spaces $C_k'(X,Y)$

We prove that for a stratifiable scattered space $X$ of finite scattered height, the function space $C_k(X)$ endowed with the compact-open topology is Baire if and only if $X$ has the Moving Off Property of Gruenhage and Ma. As a byproduct of the proof we establish many interesting Baire category properties of the function spaces $C_k'(X,Y)=\{f\in C_k(X,Y):f(X')\subset\{*_Y\}\}$, where $X$ is a topological space, $X'$ is the set of non-isolated points of $X$, and $Y$ is a topological space with a distinguished point $*_Y$.

math.GN↗