This is a good name for one of the main reasons I’ve never really felt a desire to have an LLM rephrase/correct/review something I’ve already written. It’s the reason I’ve never used Grammarly, and turned off those infuriating “phrasing” suggestions in Microsoft Word that serve only to turn a perfectly legible sentence into the verbal equivalent of Corporate Memphis.

I’m not a writer, but lately I often deliberately edit myself less than usual, to stay as far as possible from the semantic “valley floor” along which LLM text tends to flow. It probably makes me sound a bit unhinged at times, but hey at least it’s slightly interesting to read.

I do wish the article made it clear if this is an existing term (or even phenomenon) among academics, something the author is coining as of this article, or somewhere in between.

---

GPT-4o mini, “Rephrase the below text in a neutral tone”:

This name is appropriate for one key reason: I have not felt the need to use an LLM for rephrasing, correcting, or reviewing my writing. This is also why I have not utilized Grammarly and have disabled the “phrasing” suggestions in Microsoft Word, which often transform a clear sentence into something overly corporate or generic.

Although I wouldn’t categorize myself as a writer, I have been intentionally editing myself less than usual lately to avoid the typical style associated with LLM-generated text. This approach might come across as unconventional at times, but it can also make for more engaging reading.

I also wish the article clarified whether this term is already established in academic circles, if the author is introducing it for the first time, or if it falls somewhere in between.

“avoid the typical style associated with LLM-generated text” – slop!