aiscientists-dev/academic-humanizer

     

なぜこれを作ったのか

私たちの中には多くの論文や助成金申請書を書く人もいて、私たちのチームはAIを活用して支援し始めました ドラフト。問題は、AI支援のドラフトが一般的で冗長で、「近年…」といった内容になってしまうことです。 冒頭、誇張された表現、そして長すぎる文。また、作者自身の声からも逸れてしまいます 精度奨学金を失うかどうかは依存します。

「ヒューマナイザー」と呼ばれるツールもありますが、それらはブログやマーケティング用に作られています。紙上で実行してみてください。 NSFの提案であり、他のすべてとともに精度を平坦化させてしまいます。慎重な表現、学術者 書くことは最初に失われるものです。

そこで私たちは自分たちのドラフトを作成しました。キャリブレーションのために、AIに自分のドラフトとチームのドラフトを比較させました 受理された書類と資金提供された提案書を手作業で確認しました。特別なものではありません。 そして、ゲームのレビューや検知器の無効化、偽の新奇性を加えることが目的ではありません。私たちはAI支援を求めていました 著者自身の声で明確に読むための草稿、番号、引用、主張が残されたもの まさに書かれている通りです。

倫理と開示

これは明確さと声のため、著者自身の既に受け入れられた作品に合わせて調整された編集補助です。

Why we built this

Some of us write a lot of papers and grant proposals, and our team started using AI to help with drafts. The problem is that AI-assisted drafts come out generic and verbose, with “In recent years…” openers, inflated phrasing, and over-long sentences. They also drift from the author’s own voice and lose the precision scholarship depends on.

There are tools called “humanizers,” but they are built for blogs and marketing. Run one on a paper or an NSF proposal and it flattens the precision along with everything else. The careful wording academic writing depends on is the first thing to go.

So we put together our own. To calibrate it, we had the AI compare its own drafts with our team’s accepted papers and funded proposals, and we went through the differences by hand. It is nothing fancy, and it is not about gaming review, defeating detectors, or adding fake novelty. We wanted AI-assisted drafts to read clearly and in the author’s own voice, with the numbers, citations, and claims left exactly as written.

Ethics and disclosure

This is an editing aid for clarity and voice, calibrated to an author’s own prior accepted work. It does not generate findings, invent data, or change citations, and it is not designed to evade AI-use detection. Using it does not remove your obligation to disclose AI assistance: always follow the disclosure policy of the venue you submit to.

See it work

[!CAUTION] Before (a generic AI draft):

In recent years, continual learning has attracted increasing attention and achieved remarkable success. However, existing methods still face crucial challenges. In this proposal, we propose a novel framework that leverages cutting-edge techniques to delve into these intricate problems, paving the way for a transformative paradigm that will revolutionize the field.

[!TIP] After (clear, in the author’s voice, with claims tied to evidence):

Continual learning matters, but today’s methods stay empirical and their principles are unclear. That limits reliability and progress. This proposal builds a principled framework on three fronts: adaptation, soft supervision, and cross-domain knowledge. We demonstrate it on autonomous driving and network management.

More before/after passes are in examples/before-after.md: a general