作者位次 #3/4ACL 2026Findings· Findings of ACL
Beyond Memorization: Testing LLM Reasoning on Unseen Theory of Computation Tasks
Shlok Shelat · Jay Raval · Souvik Roy · Manas Gaur
摘要
Large language models (LLMs) have demonstrated strong performance on formal language tasks, yet whether this reflects genuine symbolic reasoning or pattern matching on familiar constructions remains unclear. We introduce a benchmark for deterministic finite automata (DFA) construction from regula...