MUCnoHARM@GermEval Shared Task 2026: Retrieval-based In-Context Learning for Defamatory Offences, and Where It Falls Short
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Overview of the GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments
We present the GermEval 2021 shared task on the identification of toxic, engaging, and fact-claiming comments. This shared task comprises three binary classification subtasks with the goal to identify: toxic comments, en…
Binary ClassificationFact CheckingHunterSpeechLab at GermEval 2021: Does Your Comment Claim A Fact? Contextualized Embeddings for German Fact-Claiming Comment Classification
In this paper we investigate the efficacy of using contextual embeddings from multilingual BERT and German BERT in identifying fact-claiming comments in German on social media. Additionally, we examine the impact of form…
Fact-Claiming Comment ClassificationMulti-Task LearningWLV-RIT at GermEval 2021: Multitask Learning with Transformers to Detect Toxic, Engaging, and Fact-Claiming Comments
This paper addresses the identification of toxic, engaging, and fact-claiming comments on social media. We used the dataset made available by the organizers of the GermEval-2021 shared task containing over 3,000 manually…
AIT_FHSTP at GermEval 2021: Automatic Fact Claiming Detection with Multilingual Transformer Models
Spreading ones opinion on the internet is becoming more and more important. A problem is that in many discussions people often argue with supposed facts. This year’s GermEval 2021 focuses on this topic by incorporating a…
IRCologne at GermEval 2021: Toxicity Classification
In this paper, we describe the TH Köln’s submission for the Shared Task on the Identification of Toxic Comments at GermEval 2021. Toxicity is a severe and latent problem in comments in online discussions. Complex languag…
ClassificationLanguage ModelingLanguage ModellingToxic Comment Classification