ML Paper Humanizer — AI skill for Claude Code

ml-paper-humanizer

**An agent skill for writing and revising ML conference papers across Claude Code, Codex, and other AI coding assistants—removing LLM tells so your paper reads like a human wrote it.**

[中文](README.zh-CN.md) · [Full example](examples/results-2504.13837.md)

---

Highlights

Out-of-the-box LLMs struggle with academic writing, often defaulting to inflated claims, mechanical transitions, and unnatural phrasing. Rather than relying on a brittle list of banned words, `ml-paper-humanizer` governs the writing process through corpus-backed phrasing, structural rhetoric, and strict terminology guardrails.

1. Corpus-Backed Phrasing from 307 Award & Oral Papers

We analyzed the full text of all 307 award-winning and Oral papers published between 2023 and 2026 across 12 premier venues (**NeurIPS, ICML, ICLR, ACL, EMNLP, NAACL, COLM, CVPR, ICCV, ECCV, AAAI, and KDD**). From this corpus, we extracted 1,234 recurring rhetorical patterns—each appearing in at least six distinct papers—categorized by communicative function (e.g., referencing figures, reporting empirical results, scoping claims, and contrasting baselines).

• Empirical Grounding: A comparative analysis of 60 original human paragraphs against 318 LLM-generated drafts revealed that the "LLM accent" stems largely from missing these exact functional idioms.
• Outcome: The resulting prose relies on standard phrases that reviewers have read hundreds of times, eliminating expressions invented by language models.

2. Structural Principles from Definitive Writing Guides

Clear academic prose is defined by how information is structured, not just word choice. We distilled the mechanics most frequently mishandled by LLMs from seven authoritative texts, including Gopen & Swan's *The Science of Scientific Writing*, Williams' *Style*, Swales & Feak's *Academic Writing for Graduate Students*, and Strunk's *The Elements of Style*.

• Syntactic Mechanics: Places new information at sentence endi