AI RESEARCH
From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks
arXiv CS.CL
•
ArXi:2604.00778v1 Announce Type: new Large language models (LLMs) exhibit failures on elementary symbolic tasks such as character counting in a word, despite excelling on complex benchmarks. Although this limitation has been noted, the internal reasons remain unclear. We use character counting (e.g., "How many p's are in apple?") as a minimal, controlled probe that isolates token-level reasoning from higher-level confounds.