arXiv subjects

Haoze Guo

Publications and source records attributed to Haoze Guo.

8 recordsLinked to original sources

arXiv2026

The Privacy Placebo: Diagnosing Consent Burden through Performative Scrolling

While consent banners and privacy policies invite users to read and choose, many choices are shaped by repeated, low-yield interaction routines rather than deliberation. This paper studies performative scrolling: slow, low-information interaction that can signal attention to consent without substantially improving understanding. We present the Performative Scrolling Index (PSI), a reproducible interface-audit metric for measuring pre-choice burden before a meaningful non-accepting alternative becomes visible and actionable. PSI decomposes burden into four observable components: distance, time, focus loops, and hidden reveals. In this paper, PSI is the primary burden metric, while companion signals such as AAI, CSI, and divergence are used as secondary interpretive audit aids rather than standalone validated scales. We also provide a least-effort audit protocol, design-side invariants, a worked example, and a medium-scale live deployment across desktop and mobile conditions under pointer and keyboard traversal policies. Together, these analyses show how structural choices such as offscreen alternatives, fragmented disclosure, and staged modal flows can increase pre-choice friction without improving meaningful control. PSI is not a measure of comprehension or legal sufficiency; rather, it is a diagnostic of interface-side burden intended to support reproducible audits and redesigns.

cs.HC↗

arXiv2026

Behind the Feed: A Taxonomy of User-Facing Cues for Algorithmic Transparency in Social Media

People who use social media are learning about how the companies that run these platforms make their decisions on who gets to see what through visual indicators in the interface (UI) of each social media site. These indicators are different for each platform and are not always located in an easy-to-find location on the site. Therefore, it is hard for someone to compare different social media platforms or determine whether transparency leads to greater accountability or only leads to increased understanding. A new classification system has been developed to help provide a standard way of categorizing the way, that an algorithm is presented through UI elements and whether the company has provided any type of explanation as to why they are featured. This new classification system includes the following three areas of development: design form, information content, and user agency. This new classification system can be applied to the six social media platforms currently available and serves as a reference database for identifying common archetypes of features in the each social media platform's UI. The new classification system will assist in determining whether or not the transparency of an algorithm functions the way that it was intended when it was developed and provide future design ideas that can help improve the inspectibility, actionability, and contestability of algorithms.

cs.HC↗

arXiv2026

From OCR to Analysis: Tracking Correction Provenance in Digital Humanities Pipelines

Optical Character Recognition (OCR) is a critical but error-prone stage in digital humanities text pipelines. While OCR correction improves usability for downstream NLP tasks, common workflows often overwrite intermediate decisions, obscuring how textual transformations affect scholarly interpretation. We present a provenance-aware framework for OCR-corrected humanities corpora that records correction lineage at the span level, including edit type, correction source, confidence, and revision status. Using a pilot corpus of historical texts, we compare downstream named entity extraction across raw OCR, fully corrected text, and provenance-filtered corrections. Our results show that correction pathways can substantially alter extracted entities and document-level interpretations, while provenance signals help identify unstable outputs and prioritize human review. We argue that provenance should be treated as a first-class analytical layer in NLP for digital humanities, supporting reproducibility, source criticism, and uncertainty-aware interpretation.

cs.HC↗

arXiv2026

Temporal Drift in Privacy Recall: Users Misremember From Verbatim Loss to Gist-Based Overexposure

With social media content traversing the different platforms, occasionally resurfacing after periods of time, users are increasingly prone to unintended disclosure resulting from a misremembered acceptance of privacy. Context collapse and interface cues are two factors considered by prior researchers, yet we know less about how time-lapse basically alters recall of past audiences destined for exposure. Likewise, the design space for mitigating this temporal exposure risk remains underexplored. Our work theorizes temporal drift in privacy recall as verbatim memory of prior settings blowing apart and eventually settling with gist-based heuristics, which more often than not select an audience larger than the original one. Grounded in memory research, contextual integrity, and usable privacy, we examine why such a drift occurs, why it tends to bias toward broader sharing, and how it compounds upon repeat exposure. Following that, we suggest provenance-forward interface schemes and a risk-based evaluation framework that mutates recall into recognition. The merit of our work lies in establishing a temporal awareness of privacy design as an essential safety rail against inadvertent overexposure.

cs.HC↗

arXiv2026

ConsentDiff at Scale: Longitudinal Audits of Web Privacy Policy Changes and UI Frictions

Web privacy is experienced via two public artifacts: site utterances in policy texts, and the actions users are required to take during consent interfaces. In the extensive cross-section audits we've studied, there is a lack of longitudinal data detailing how these artifacts are changing together, and if interfaces are actually doing what they promise in policy. ConsentDiff provides that longitudinal view. We build a reproducible pipeline that snapshots sites every month, semantically aligns policy clauses to track clause-level churn, and classifies consent-UI patterns by pulling together DOM signals with cues provided by screenshots. We introduce a novel weighted claim-UI alignment score, connecting common policy claims to observable predicates, and enabling comparisons over time, regions, and verticals. Our measurements suggest continued policy churn, systematic changes to eliminate a higher-friction banner design, and significantly higher alignment where rejecting is visible and lower friction.

cs.HC↗

arXiv2026

Hidden-in-Plain-Text: A Benchmark for Social-Web Indirect Prompt Injection in RAG

Retrieval-augmented generation (RAG) systems put more and more emphasis on grounding their responses in user-generated content found on the Web, amplifying both their usefulness and their attack surface. Most notably, indirect prompt injection and retrieval poisoning attack the web-native carriers that survive ingestion pipelines and are very concerning. We provide OpenRAG-Soc, a compact, reproducible benchmark-and-harness for web-facing RAG evaluation under these threats, in a discrete data package. The suite combines a social corpus with interchangeable sparse and dense retrievers and deployable mitigations - HTML/Markdown sanitization, Unicode normalization, and attribution-gated answered. It standardizes end-to-end evaluation from ingestion to generation and reports attacks time of one of the responses at answer time, rank shifts in both sparse and dense retrievers, utility and latency, allowing for apples-to-apples comparisons across carriers and defenses. OpenRAG-Soc targets practitioners who need fast, and realistic tests to track risk and harden deployments.

cs.CR↗

arXiv2025

Simulating Teams with LLM Agents: Interactive 2D Environments for Studying Human-AI Dynamics

Enabling users to create their own simulations offers a powerful way to study team dynamics and performance. We introduce VirTLab, a system that allows researchers and practitioners to design interactive, customizable simulations of team dynamics with LLM-based agents situated in 2D spatial environments. Unlike prior frameworks that restrict scenarios to predefined or static tasks, our approach enables users to build scenarios, assign roles, and observe how agents coordinate, move, and adapt over time. By bridging team cognition behaviors with scalable agent-based modeling, our system provides a testbed for investigating how environments influence coordination, collaboration, and emergent team behaviors. We demonstrate its utility by aligning simulated outcomes with empirical evaluations and a user study, underscoring the importance of customizable environments for advancing research on multi-agent simulations. This work contributes to making simulations accessible to both technical and non-technical users, supporting the design, execution, and analysis of complex multi-agent experiments.

cs.HC↗

arXiv2025

VirtLab: An AI-Powered System for Flexible, Customizable, and Large-scale Team Simulations

Simulating how team members collaborate within complex environments using Agentic AI is a promising approach to explore hypotheses grounded in social science theories and study team behaviors. We introduce VirtLab, a user-friendly, customizable, multi-agent, and scalable team simulation system that enables testing teams with LLM-based agents in spatial and temporal settings. This system addresses the current frameworks' design and technical limitations that do not consider flexible simulation scenarios and spatial settings. VirtLab contains a simulation engine and a web interface that enables both technical and non-technical users to formulate, run, and analyze team simulations without programming. We demonstrate the system's utility by comparing ground truth data with simulated scenarios.

cs.HC↗