English(EN) SarcasTraps: Effect of Sarcasm on Turkish Hate Speech Detection

讽刺阻碍了大型语言模型和微调模型对土耳其仇恨言论的检测

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

一项新的研究论文介绍了 SarcasTraps，这是一个旨在评估讽刺如何影响土耳其仇恨言论检测的数据集。研究发现，讽刺显著挑战了 BERTurk 和 XLM-RoBERTa 等微调模型，以及 GPT-4.1 和 Llama 3.3 70B Instruct 等大型语言模型，导致在识别讽刺性仇恨言论时召回率或精确率降低。 AI

影响凸显了人工智能在安全应用中理解讽刺等细微语言方面的挑战。

排序理由介绍新数据集的研究论文，以及在该数据集上对模型的评估。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 介绍新数据集的研究论文，以及在该数据集上对模型的评估。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Niyazi Ahmet Metin, Dilara Kek\"ull\"uo\u{g}lu · 2026-10-15 04:00

SarcasTraps：讽刺对土耳其仇恨言论检测的影响

arXiv:2610.16957v1 Announce Type: cross Abstract: Standard hate speech detection datasets often emphasize explicit harmful language, but directed harm can also be expressed indirectly, without clearly hateful wording. Sarcasm is one such form of indirect expression, as it can con…

本文如何被排名

报道来源 [1]

SarcasTraps：讽刺对土耳其仇恨言论检测的影响

相关实体

相关话题