Algospeak, Hiding in the Open: The Trade-off Between Legible Meaning and Detection Avoidance
For researchers studying linguistic evasion in AI-mediated communication, this work provides a formal framework and empirical methodology to analyze the Algospeak trade-off, though it is an incremental step based on existing taxonomies.
This paper formalizes the trade-off between understandability and detection avoidance in Algospeak, introducing the concept of Majority Understandable Modulation (MUM). Using a dataset of 700 modulated items and evaluations with seven LLMs, they estimate the MUM threshold and characterize the relationship between modulation and understandability.
As large language models (LLMs) increasingly mediate both content generation and moderation, linguistic evasion strategies known as Algospeak have intensified the coevolution between evaders and detectors. This research formalizes the underlying dynamics grounded in a joint action model: when Algospeak increases, detectability and understandability decrease. Further, the concept of Majority Understandable Modulation (MUM) is introduced and defined as the modulation level at which additional evasive alteration increases detector evasion but loses comprehension for the majority of recipients. To empirically probe this trade-off, we introduce a reproducible framework that can be used to create meaning-preserving, Algospeak-style variants, based on an existing taxonomy and with tunable modulation levels. Using COVID-19 disinformation as a first proof-by-example setting, we construct a reference dataset of 700 modulated items, drawn from twenty base sentences across five modulation levels and seven strategies. We then run two linked evaluations with seven different language models: one testing for interpretation through meaning recovery and one for disinformation detection through classification. Curve fitting over modulation levels yields an estimate of the Majority Understandable Modulation threshold and enables sensitivity analyses across strategies and models, see Figure 1. Results reveal the characteristic relationships between understandability and modulation. This study lays the groundwork for understanding the dynamics behind Algospeak and provides the framework, dataset, and experimental setups described.