Do LMs Know What Variables Do? Interpreting Code Representations via Variable Roles
arXiv:2610.24118v1 Announce Type: new Abstract: Variable roles describe recurring behaviors such as accumulation, traversal, and retaining the best candidate encountered. We use Sajaniemi's independently defined taxonomy to study which role distinctions can be recovered from large language models,…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-20 04:00 · arXiv cs.CL
Do LMs Know What Variables Do? Interpreting Code Representations via Variable Roles