English(EN) Hate Speech Classification In Roman Urdu: A Comparative Study On Parameter Efficient Fine-Tuning And Prompt Engineering

新研究比较了罗马乌尔都语仇恨言论检测的PEFT和提示工程方法

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-25 04:00

研究人员探索了参数高效微调（PEFT）和提示工程技术在罗马乌尔都语（一种低资源语言）的仇恨言论分类中的应用。该研究通过四项实验，比较了直接LLM推理、带LoRA的PEFT、提示调优和提示工程方法。这些方法旨在改善数据有限和语言结构非正式情况下的仇恨言论检测。 AI

影响这项研究可能有助于开发更有效的低资源语言仇恨言论检测工具，从而提高在线安全性。

排序理由该集群包含一篇详细介绍特定NLP任务AI技术比较研究的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

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: 2 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍特定NLP任务AI技术比较研究的研究论文。[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: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Toneema Zubair · 2026-08-25 04:00

罗马乌尔都语中的仇恨言论分类：参数高效微调与提示工程的比较研究

arXiv:2608.21408v1 Announce Type: new Abstract: Due to the widespread accessibility of the internet and social media, toxic and hateful con-tent has grown exponentially, causing significant distress and negative societal impacts. Ro-man Urdu, a low-resource language used in Pakis…