← 研踪 PaperTrailarXiv:2611.15306 · v1
Beyond the Explicit: Benchmarking and Detecting Implicit Harm in Short Videos
首次提交 2026-11-11 18:41
版本更新 2026-11-11 18:41
雷达观测 2026-11-13 11:11
摘要
Short videos have become a dominant online medium, where harmful content is increasingly conveyed in implicit and fragmented forms. Prior work largely focuses on explicit categories, such as violence and hate speech, and often fails to detect videos that subtly promote misleading values through narrative context, emotional framing, or cross-modal cues, partly due to the lack of dedicated benchmarks for implicit harm. To bridge this gap, we construct DeepHarm-7K, a large-scale harmful short-video dataset comprising 7,110 samples annotated according to a fine-grained harmful-content taxonomy. The dataset systematically covers implicitly harmful videos across diverse real-world scenarios and is constructed through a rigorous multi-stage quality-control process. Building on this dataset, we propose DeepHarm-VL, a multimodal detection framework that integrates visual, audio, and cross-modal reasoning. The framework employs a two-round reasoning strategy to progressively identify surface-level evidence and infer latent harmful implications. Experimental results show consistent improvements over strong baselines and state-of-the-art methods across multiple open-source video-language models, demonstrating its effectiveness in detecting both explicit and implicit harmful short videos.
作者备注：9 pages, 4 figures, 8 tables
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-11 18:41 · 最新观测版本
Beyond the Explicit: Benchmarking and Detecting Implicit Harm in Short Videos
Short videos have become a dominant online medium, where harmful content is increasingly conveyed in implicit and fragmented forms. Prior work largely focuses on explicit categories, such as violence and hate speech, and often fails to detect videos that subtly promote misleading values through narrative context, emotional framing, or cross-modal cues, partly due to the lack of dedicated benchmarks for implicit harm. To bridge this gap, we construct DeepHarm-7K, a large-scale harmful short-video dataset comprising 7,110 samples annotated according to a fine-grained harmful-content taxonomy. The dataset systematically covers implicitly harmful videos across diverse real-world scenarios and is constructed through a rigorous multi-stage quality-control process. Building on this dataset, we propose DeepHarm-VL, a multimodal detection framework that integrates visual, audio, and cross-modal reasoning. The framework employs a two-round reasoning strategy to progressively identify surface-level evidence and infer latent harmful implications. Experimental results show consistent improvements over strong baselines and state-of-the-art methods across multiple open-source video-language models, demonstrating its effectiveness in detecting both explicit and implicit harmful short videos.
查看此版本解读 →查看此版本原文 ↗