LLMs maintain surface syntax for novel CFGs but fail to preserve semantics under recursion and branching, relying on keyword bootstrapping rather than pure symbolic reasoning.
Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Diagnosing CFG Interpretation in LLMs
LLMs maintain surface syntax for novel CFGs but fail to preserve semantics under recursion and branching, relying on keyword bootstrapping rather than pure symbolic reasoning.