Agents
MUCnoHARM@GermEval Shared Task 2026: Retrieval-based In-Context Learning for Defamatory Offences, and Where It Falls Short
arXiv:2609.09791v1 Announce Type: new Abstract: With hate speech being ubiquitous online, automatic detection is crucial, in particular when it comes to criminally relevant social media posts. We stud
arXiv:2609.09791v1 Announce Type: new 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 {S}{S} 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.
Related
- Learning Sexism Detection Using Multi-Agent Perspectivist Preference Optimization
- Query-Adaptive Semantic Chunking for Retrieval-Augmented Generation: A Dynamic Strategy with Contextual Window Expansion
- When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval
Source: arXiv cs.CL | 2026-09-10