@inproceedings{hoeken-etal-2026-prompting,
    title = "Prompting Across Time: Evaluating {LLM}s on Historical and Contemporary Offensive Language",
    author = "Hoeken, Sanne  and
      Spliethoff, Sophie Jasmin  and
      Schwandt, Silke  and
      Alacam, {\textbackslash}{''}Ozge  and
      Zarrie{\{}{\textbackslash}ss{\}}, Sina",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1665/",
    pages = "33295--33314",
    ISBN = "979-8-89176-395-1",
    abstract = "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. Fine-tuned 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."
}