Syntax hacking: Researchers discover sentence structure can bypass AI safety rules

Researchers from MIT, Northeastern University, and Meta recently released a paper suggesting that large language models (LLMs) similar to those that power ChatGPT may sometimes prioritize sentence structure over meaning when answering questions. The findings reveal a weakness in how these models process instructions that may shed light on why some prompt injection or jailbreaking approaches work, though the researchers caution their analysis of some production models remains speculative since training data details of prominent commercial AI models are not publicly available.

The team, led by Chantal Shaib and Vinith M. Suriyakumar, tested this by asking models questions with preserved grammatical patterns but nonsensical words. For example, when prompted with “Quickly sit Paris clouded?” (mimicking the structure of “Where is Paris located?”), models still answered “France.”

This suggests models absorb both meaning and syntactic patterns, but can overrely on structural shortcuts when they strongly correlate with specific domains in training data, which sometimes allows patterns to override semantic understanding in edge cases. The team plans to present these findings at NeurIPS later this month.

As a refresher, syntax describes sentence structure—how words are arranged grammatically and what parts of speech they use. Semantics describes the actual meaning those words convey, which can vary even when the grammatical structure stays the same.

Semantics depends heavily on context, and navigating context is what makes LLMs work. The process of turning an input, your prompt, into an output, an LLM answer, involves a complex chain of pattern matching against encoded training data.

To investigate when and how this pattern-matching can go wrong, the researchers designed a controlled experiment. They created a synthetic dataset by designing prompts in which each subject area had a unique grammatical template based on part-of-speech patterns. For instance, geography questions followed one structural pattern while questions about creative works followed another. They then trained Allen AI’s Olmo models on this data and tested whether the models could distinguish between syntax and semantics.