Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation

ArXi:2605.25520v1 Announce Type: new Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those labels is unclear. We investigate this in Natural Language Inference using controlled premise-hypothesis pairs that differ by a single semantic transformation.