1 citations · 2 across the 20 of their papers we have counts for
7 papers · 1 filter
Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation
Junyu Lu, Kaiyuan Liu, Jingyi Kang +7
Large language models (LLMs) are increasingly used for hate speech moderation, often within human--AI workflows in which reviewers provide feedback before a final decision. Such fe…
Decoding Multimodal Cues: Unveiling the Implicit Meaning Behind Hateful Videos
Junyu Lu, Deyi Ji, Liqun Liu +9
Hateful videos have become prevalent on online platforms, highlighting an urgent need for effective detection. However, existing studies primarily focus on binary classification an…
Self-signals Driven Multi-LLM Debate for Efficient and Accurate Reasoning
Xuhang Chen, Zhifan Song, Deyi Ji +2
Large Language Models (LLMs) have exhibited impressive capabilities across diverse application domains. Recent work has explored Multi-LLM Agent Debate (MAD) as a way to enhance pe…
Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis
Junyu Lu, Deyi Ji, Xuanyi Liu +5
Large language models for subjectivity analysis are typically trained with aggregated labels, which compress variations in human judgment into a single supervision signal. This par…
ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring
Deyi Ji, Junyu Lu, Xuanyi Liu +7
Online advertising governance faces significant challenges due to the non-stationary nature of regulatory policies, where emerging mandates (e.g., restrictions on education or aest…
RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning
Deyi Ji, Yuekui Yang, Haiyang Wu +3
Advertisement (Ad) video violation detection is critical for ensuring platform compliance, but existing methods struggle with precise temporal grounding, noisy annotations, and lim…