arXiv subjects

Changxi Wen

Publications and source records attributed to Changxi Wen.

3 recordsLinked to original sources

arXiv2026

Towards Multi-Agent-Simulation-Based Community Note Evaluation

Community-based fact-checking that relies on cross-consensus is expanding rapidly on social media platforms. However, the delay and low-ratio of cross-consensus community fact-checks rated by human contributors remains a significant challenge. To address this, we first created ComRate, a large-scale dataset comprising 2.5 million community notes and over 209 million ratings sourced from $\mathbb{X}$. We then propose MultiCom, a persona-guided multi-agent rating framework for community note evaluation. MultiCom simulates diverse rater population by clustering contributors in a matrix-factorized rater space and prompting persona agents to generate structured assessments based on the official community notes rating schema. These agents output structured and explainable judgments, such as confidence, agreement signals and reasons. An out-of-fold calibrated aggregation algorithm combines features such as raw votes and diagnostic reason signals for reliable prediction. Extensive evaluations demonstrate that MultiCom outperforms alternative methods, achieving an average accuracy of 84.7% (balanced accuracy 68.3%, macro-F1 60.1%) on the evaluation set.

cs.SI↗

arXiv2026

Investigating Novice Researchers' Perceptions of Research Privacy Within LLM-Assisted Workflows

Large Language Model (LLMs)-assisted scholarly workflows introduce critical privacy and intellectual property risks. As a uniquely vulnerable cohort driven by publication pressure and a lack of institutional support, novice researchers rely heavily on public LLMs, compelling them to navigate high-stakes privacy-publication trade-offs. To investigate these concerns, we conducted semi-structured interviews with 44 researchers across diverse disciplines. Our findings reveal that the fear of idea leakage paradoxically accelerates, rather than deters, reliance on LLMs, as researchers utilize them to expedite publication. They also held misconceptions that their ideas lacked the unique value to attract targeted attacks, and that their inputs would be safely diluted within massive datasets, preventing reconstruction. From interviews, we identified five types of mitigations including input fragmentation and adversarial probing, though we found that participants largely perceived these measures as ineffective. We outline implications including implementing institution-level sandboxed isolation, scenario-based privacy pedagogy, and verifiable data-deletion audits for transparency.

cs.HC↗

arXiv2025

The Pervasive Blind Spot: Benchmarking VLM Inference Risks on Everyday Personal Videos

The proliferation of Vision-Language Models (VLMs) introduces profound privacy risks from personal videos. This paper addresses the critical yet unexplored inferential privacy threat, the risk of inferring sensitive personal attributes over the data. To address this gap, we crowdsourced a dataset of 508 everyday personal videos from 58 individuals. We then conducted a benchmark study evaluating VLM inference capabilities against human performance. Our findings reveal three critical insights: (1) VLMs possess superhuman inferential capabilities, significantly outperforming human evaluators, leveraging a shift from object recognition to behavioral inference from temporal streams. (2) Inferential risk is strongly correlated with factors such as video characteristics and prompting strategies. (3) VLM-driven explanation towards the inference is unreliable, as we revealed a disconnect between the model-generated explanations and evidential impact, identifying ubiquitous objects as misleading confounders.

cs.HC↗