Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection
2026-06-25 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied how people use indirect language to hide sensitive meanings on social media to avoid moderation. They created a new system that classifies these hidden expressions based on how the meaning is encoded, rather than why it is used. They tested their system on posts from TikTok and Bluesky and found it worked better than existing methods in detecting these disguised messages. Their work shows that focusing on the underlying language mechanisms helps improve automated detection of tricky or coded content online.
indirect linguistic expressionscontent moderationalgospeakeuphemismscoded languagelarge language modelsTikTokBlueskyclassification taxonomy
Authors
Hamid Reza Firoozfar, Mohammadsadegh Abolhasani, Reza Mousavi, Paul Jen-Hwa Hu
Abstract
To avoid moderation and surveillance on social media, some users routinely invent indirect linguistic expressions (ILE) that camouflage sensitive meanings. Such expressions surface as algospeak, euphemisms, and adversarial obfuscation, depending on intent and context, and they involve recurring encoding mechanisms. We propose a comprehensive, mechanism-oriented taxonomy of ILE that abstracts away from communicative goals and instead categorizes the underlying operations through which meaning is encoded and recovered. We evaluate the taxonomy by incorporating it into LLM prompts and comparing it with four existing taxonomies and a no-taxonomy baseline, using 2,000 manually annotated TikTok and Bluesky posts. The proposed taxonomy attains the strongest document- and span-level performance across the three LLMs, achieving an improvement of 4.7% in accuracy and 5.4% in F1 over the best-performing benchmark. The empirical results reveal the importance of a comprehensive, mechanism-oriented taxonomy as a stable scaffold for detecting emerging coded language and a useful input to content moderation. Disclaimer: This paper contains content that may be profane, vulgar, or offensive.