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

arXiv:2606.27314 · cs.CL · Submitted 2026-06-25 · Read on arXiv

cs.CL

Submitted: 2026-06-25

Updated: 2026-09-13

Comments: Submitted for review in ARR for EMNLP 2026

Code: https://github.com/hmdfiroozfar/mechanism-oriented-ile-taxonomy

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 23× in this paper · explained in 2 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• Ablation — 4× in this paper · explained in 1 episode
• Abstraction — 3× in this paper · explained in 1 episode
• Workshop on Figurative Language Processing — 3× in this paper
• Annotator Agreement — 2× in this paper · explained in 1 episode
• Grounding — 2× in this paper · explained in 3 episodes
• Pragmatics — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Concept Drift — 1× in this paper · explained in 4 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs
• Synthetic and Natural Noise Both Break Neural Machine Translation
• The Benefits of Label-Description Training for Zero-Shot Text Classification
• Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions
• Combating Adversarial Misspellings with Robust Word Recognition
• Euphemistic Phrase Detection by Masked Language Model

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering