Entity · paper

Understanding Interpretation Difficulty in Harmful Online Communication: Insights from Cybercrime Communities

paperactiveprovisionalunderstanding-interpretation-difficulty-in-harmful-online-communication-insights-from-cybercrime-communities-7e8eab06·1 events·first seen Jul 9, 2026

Aliases: Understanding Interpretation Difficulty in Harmful Online Communication: Insights from Cybercrime Communities

Co-occurring entities

Discord

More like this (12)

Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models AIMO Interpretability Challenge SkillHarm Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats From Self to Other: Evaluating Demographic Perspective-Taking in LLM Hate Speech Annotation Beyond Accuracy: Community Perspectives on Machine Translation Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation From Celebrities to Anyone: Characterizing AI Nudification Content, Technology, and Community Dynamics on 4chan

Recent events (1)

4arXiv · cs.CL·Jul 9, 2026·source ↗

Study evaluates LLM and human interpretation of coded language in cybercrime Discord chats

Researchers present an exploratory study on interpretation difficulty in cybercrime-related Discord chats, focusing on slang, coded terms, and community-specific expressions. The study constructs expert-reviewed reference interpretations and uses them to benchmark both human and LLM performance under varying context conditions. Key findings: local context alone is insufficient for humans, while extended conversational context and external knowledge substantially help; larger LLMs outperform smaller ones; the authors propose a preliminary taxonomy of factors driving interpretation difficulty. The work argues that harmful-content analysis should be framed as evidence-integration rather than message-level classification.

Evaluation and Benchmarking AI Safety Research Discord Understanding Interpretation Difficulty in Harmful Online Communication: Insights from Cybercrime Communities