paper

Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection

paperactiveprovisional

beyond-surface-forms-a-comprehensive-mechanism-oriented-taxonomy-of-indirect-linguistic-encoding-for-llm-based-coded-language-detection-d980adcd

·1 events·first seen 3d ago

Aliases: Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection

Co-occurring entities

Bluesky TikTok

More like this (12)

Operadic consistency: a label-free signal for compositional reasoning failures in LLMs The Signal-Coverage Matrix: Stratifying Type and Semantic Errors in Statement Autoformalization LCO-Embedding Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs Transformer Language Models Latent Context Language Models code synthesis LLMs Recursive Language Models (RLMs)Reasoning Language Models Consensus-based Agentic Large Language Model Framework for Harmonized Tariff Schedule Code Classification Causally Evaluating the Learnability of Formal Language Tasks Words as Difference Makers: How Large Language Models Determine Causal Structure in Text

Recent events (1)

4arXiv · cs.CL·3d ago·source ↗

Mechanism-oriented taxonomy of indirect linguistic encoding improves LLM-based coded language detection

Researchers propose a comprehensive taxonomy of indirect linguistic expressions (ILE) — covering algospeak, euphemisms, and adversarial obfuscation — organized by underlying encoding mechanisms rather than communicative intent. The taxonomy is evaluated by injecting it into LLM prompts and benchmarked against four existing taxonomies and a no-taxonomy baseline on 2,000 manually annotated TikTok and Bluesky posts. The proposed taxonomy achieves 4.7% accuracy and 5.4% F1 improvements over the best competing approach across three LLMs, suggesting structured linguistic scaffolding meaningfully aids content moderation tasks.

Evaluation and Benchmarking AI Safety Research Bluesky TikTok Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection