Lune

ACL Findings2026

Prompting Across Time: Evaluating LLMs on Historical and Contemporary Offensive Language

Sanne Hoeken, Sophie Jasmin Spliethoff, Silke Schwandt, Özge Alaçam, Sina Zarrieß

摘要

Research on hate speech detection (HSD) has centered on modern data, even though offensive language has a much longer history. This paper presents the first systematic evaluation of instruction-tuned LLMs on Early Modern English invectives, compared with a modern hate-speech benchmark. Our work applies a modular prompt design to measure the contribution of definitional richness, contextual grounding, decision rules and few-shot examples. The results indicate that clearer annotation boundaries in the curated historical corpus lead to higher classification performance compared to the modern benchmark, despite the disadvantage of linguistic unfamiliarity. Prompt brittleness, however, persists across both domains. Classification-oriented components (rules, examples) drive the strongest effects, while definitional or contextual additions matter less. Finetuned encoder models still outperform LLMs, but some prompt configurations can narrow the gap. Overall, our study provides practical guidance for prompt design in both digital humanities and HSD and new opportunities for tracing the historical development of hate speech. 1

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

可以从这些问题问起

Lune 可以查阅

全文 · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • fBERT: A Neural Transformer for Identifying Offensive Content 引用了 Unsupervised Cross-lingual Representation Learning at Scale
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

它引用的 Paper4

  1. Unsupervised Cross-lingual Representation Learning at ScaleAlexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary 等ACL 2020 · 539 次引用
  2. fBERT: A Neural Transformer for Identifying Offensive ContentDiptanu Sarkar, Marcos Zampieri, Tharindu Ranasinghe, Alexander G. Ororbia IIEMNLP Findings 2021 · 43 次引用
  3. Probing LLMs for hate speech detection: strengths and vulnerabilitiesSarthak Roy, Ashish Harshavardhan, Animesh Mukherjee, Punyajoy SahaEMNLP Findings 2023 · 23 次引用
  4. A Survey of Uncertainty Estimation Methods on Large Language ModelsZhiqiu Xia, Jinxuan Xu, Yuqian Zhang, Hang LiuACL Findings 2025 · 16 次引用

相关 Paper

  1. SAHSD: Enhancing Hate Speech Detection in LLM-Powered Web Applications via Sentiment Analysis and Few-Shot LearningYulong Wang, Hong Li, Ni WeiWWW 2025 · 2 次引用
  2. Who Speaks Matters: Analysing the Influence of the Speaker's Linguistic Identity on Hate ClassificationAnanya Malik, Kartik Sharma, Shaily Bhatt, Lynnette Hui Xian NgEMNLP Findings 2025
  3. HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language ModelsHuy Nghiem, Hal Daumé IIIEMNLP Findings 2024 · 10 次引用
  4. Legally Enforceable Hate Speech Detection for Public ForumsChu Fei Luo, Rohan Bhambhoria, Samuel Dahan, Xiaodan ZhuEMNLP Findings 2023 · 9 次引用
  5. Evaluating Large Language Models for Detecting AntisemitismJay Patel, Hrudayangam Mehta, Jeremy BlackburnEMNLP 2025 · 1 次引用
黄昏的海面,两侧是细线勾勒的悬崖