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

arXiv: https://arxiv.org/abs/2609.09791 · HTML: https://mlsanity.com/paper/2609.09791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 44 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction](https://mlsanity.com/paper/2307.08321/) (2023)
- [Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks](https://mlsanity.com/paper/2305.08714/) (2023)
- [Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction](https://mlsanity.com/paper/2407.01964/) (2024)
- [Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset](https://mlsanity.com/paper/2403.19559/) (2024)
- [A Legal Approach to Hate Speech: Operationalizing the EU's Legal Framework against the Expression of Hatred as an NLP Task](https://mlsanity.com/paper/2004.03422/) (2020)
- [Making FETCH! Happen: Finding Emergent Dog Whistles Through Common Habitats](https://mlsanity.com/paper/2412.12072/) (2024)
- [Conditioning Large Language Models on Legal Systems? Detecting Punishable Hate Speech](https://mlsanity.com/paper/2506.03009/) (2025)
- [The Unintended Trade-off of AI Alignment:Balancing Hallucination Mitigation and Safety in LLMs](https://mlsanity.com/paper/2510.07775/) (2025)
- [Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection](https://mlsanity.com/paper/2509.00673/) (2025)
- [Beyond Imperfect Alternatives with Rulemapping: A Neuro-Symbolic Case Study on Online Hate Speech](https://mlsanity.com/paper/2605.16280/) (2026)

## Abstract (arXiv)

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 SS 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.