Home | Publications | GMA26

MUCnoHARM@GermEval Shared Task 2026: Retrieval-Based In-Context Learning for Defamatory Offences, and Where It Falls Short

MCML Authors

Abstract

With hate speech being ubiquitous online, automatic detection is crucial, in particular when it comes to criminally relevant social media posts. We study a variety of retrieval-based in-context learning (RetICL) strategies for detecting defamatory offences under §§ 185-187 StGB (the subject of GermEval 2026 Subtask 4). Few-shot prompting beats zero-shot, but retrieval-based approaches offer only marginal gains over random demonstrations, and even fall behind an optimised static set of demonstrations. Providing concrete legal knowledge helps, yet model choice outweighs every other system choice. Models over-predict criminal relevance while still missing 26-57% of criminally relevant posts, suiting them for triage rather than autonomous moderation.

inproceedings GMA26


GermEval @KONVENS 2026

Shared Task on Harmful Content Detection in German Social Media at the 22th Conference on Natural Language Processing. Hamburg, Germany, Sep 14-17, 2026. To be published. Preprint available.

Authors

K. Gnadt • M. Meidinger • M. Aßenmacher

Links

arXiv GitHub

Research Area

 A1 | Statistical Foundations & Explainability

BibTeXKey: GMA26

Back to Top