# Code comment narration and over-explanation > Source-anchored research for Code comment narration and over-explanation. Run status: COMPLETED. Parent: [LLM tells in code, commit messages, comments and READMEs](https://llms-explorer.com/tree/ai-isms-code-and-commit-tells/) · 4 facets · 5 facts · page: https://llms-explorer.com/tree/code-comment-narration-and-over-explanation/ ## Definitions - The characteristic narration tell is a comment that restates the adjacent code, adding maintenance burden and burying the few comments that matter. (low confidence) — [source](https://github.com/takahirox/my-ai-employee/issues/76) - Comment-based detection is a weak, proxy signal: the repository study calls its results proxy-based and warns detectors both under- and over-estimate LLM use, and other work reports commercial detectors are affected by comments and unreliable. (medium confidence) — [source](https://arxiv.org/html/2607.01867v1) ## Structure and components - Agent guidance for avoiding the tell: do not add comments by default; add one only for non-obvious why (rationale, constraints, invariants, trade-offs, surprising external behavior); prefer better names, types and structure over narration. (low confidence) (verified as of 2026-09-04) — [source](https://github.com/takahirox/my-ai-employee/issues/76) ## Measurements and reference values - LLM comments are not uniformly poor: in a 415-comment Java evaluation, human experts judged 58.8% to match originals and 27.7% to surpass them; automated metrics such as BLEU correlated negatively with human judgment. (low confidence) — [source](https://arxiv.org/html/2408.14007v3) ## Facts and statements - A 2021-2025 study of eight GitHub repositories found comments flagged as likely LLM-generated concentrated in Meta and Explanation categories, and remained relatively stable over time. (medium confidence) (verified as of 2026-07-01) — [source](https://arxiv.org/html/2607.01867v1)