The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models

ArXi:2601.19926v2 Announce Type: replace-cross We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on over 3,000 datapoints spanning a wide range of syntactic phenomena, languages, models, and methods. We take the data to collectively show that TLMs encode a non-trivial amount of syntactic knowledge. Behavioral evidence shows strong performance on formal syntactic phenomena, but weaker and variable performance on phenomena at the syntax-semantics interface.