5
\$\begingroup\$

When writing an answer or a question on this stack, I try to be the clearest possible for exposing my problem or for proposing a solution, but I recognize two main issues1:

  • I use the same sentence structures again and again
  • My tendency is to employ the same words, again and again.

I believe that this comes from two aspects: I am not a native English speaker and my styles comes mainly from writing Math scientific paper, where the language is not very rich.

I thought then to ask for the help of Large Language Models (LMMs) such as CHATgpt, by asking something as " Improve the English of < part of question/answer >. Of course, one should check if the LLM produced a coherent writing and did not make up anything. For example, the part of one answer of mine reads;

The options presented in Table "Uthgardt Totems" are available at 3rd level, and such table shows the equivalent of these options to the animals of the original PHB's subclass and to the new option Tiger.

The new options add new totem spirits: you have to follow the same subclass rules depicted in the PHB for the choices you are taking during leveling up. This means that you can choose a Tree Ghost totem at 3rd level, and subsequently the Eagle spirit at 6th level, since the PHB rules states, for the Aspect of the Beast feature, that:

you can choose the same animal you selected at 3rd level or a different one.

and a possible outcome of chatgpt is

The choices outlined in the "Uthgardt Totems" table become accessible at the 3rd level. This table not only illustrates their counterparts among the animals featured in the original Player's Handbook (PHB) subclass but also introduces the new option, the Tiger.

These new options introduce additional totem spirits, and it's essential to adhere to the same subclass rules detailed in the PHB when making your selections during character advancement. This means that you can initially opt for the Tree Ghost totem at 3rd level and subsequently choose the Eagle spirit at 6th level, in accordance with the PHB guidelines for the Aspect of the Beast feature, which says that

you can choose the same animal you selected at 3rd level or a different one.

The meaning is the same, but the English is much better.

Can we use such LLMs for improving the English of our posts? Or should we ban it for this purpose too?

Note. I am not asking if we should allow the employment of LLMs for generating questions and answers (we already have a meta for that), but just for improving the language of a human written answer.


1 Ça va sans dire, the third issue regards typos and grammar errors...

\$\endgroup\$
8
  • 11
    \$\begingroup\$ Frame challenge: the English isn't much better after GPT punches it up. In fact, I think GPT's re-write is worse. It's identical in meaning from clause to clause (which is good, of course), but GPT often chooses needlessly-longer words or adds superfluous descriptors. "are available at 3rd level" is perfectly clear; "become accessible at the 3rd level" is no clearer but adds syllables. GPT's "initially opt for the Tree Ghost totem at 3rd level and subsequently choose the Eagle spirit at 6th level" adds "initially" and "subsequently," as if a reader needed help placing 3rd level before 6th. \$\endgroup\$
    – nitsua60 Mod
    Oct 29, 2023 at 1:51
  • 1
    \$\begingroup\$ @nitsua60 Why not put that as an answer? \$\endgroup\$
    – NotArch
    Oct 29, 2023 at 2:50
  • \$\begingroup\$ @nitsua60 Yeah, this is just an example, one can also improve the prompt, here I used just "improve", but you can use "improve with the same number of words/chars" or something similar. Of course, one has to check the final version, I saw some generated text with completely made up concepts and definitions. \$\endgroup\$
    – Eddymage
    Oct 29, 2023 at 7:57
  • \$\begingroup\$ Relevant discussion: Should this stack ban ChatGPT? \$\endgroup\$
    – V2Blast
    Oct 31, 2023 at 0:40
  • 1
    \$\begingroup\$ @NotArch looks like greener got to it before I made it back from my weekend =) \$\endgroup\$
    – nitsua60 Mod
    Oct 31, 2023 at 17:33
  • \$\begingroup\$ @nitsua60 and how! \$\endgroup\$
    – NotArch
    Oct 31, 2023 at 19:40
  • 2
    \$\begingroup\$ As a native English speaker who also "uses the same sentence structures again and again" and "employs the same words, again and again", as long as it doesn't get lead to triple-redundancy in everything you type (oops, also me), it's fine. I've read a number of your posts, and never even considered you might not be a native English speaker; what errors you make are indistinguishable from the errors any other articulate poster makes from time to time. Whether or not ChatGPT improves anything (and I agree it doesn't here), I don't want a stack with the same ChatGPT writing style for every post. \$\endgroup\$ Nov 8, 2023 at 11:33
  • 2

5 Answers 5

15
\$\begingroup\$

No, you should avoid using LLMs and ChatGPT for proofreading and for attempting to improve posts and their English. This is because it will make your posts worse, not better. Proofreading is not the function of ChatGPT and it is not something it will do for you.

The example post you gave us was already 99% fine. The GPT post doesn't make it better. It introduces weird phrasing like “at the 3rd level” which we don't use because it doesn't understand how we write in our domain. It turns a sentence into marketing talk (“not only ... but also”) which has no reason to be that way. ChatGPT also makes several things wordier for no reason and rephrases several things for no actual benefit—these are not improvements! If this were submitted as an edit, I'd roll it back and ping the editor in comments to have words with them about editing guidelines.

The only things I'd have changed in the original were the phrasing of “and such table” and probably dropping the quotes around the name, and I don't need GPT to detect that or fix it for me.

ChatGPT was made for chat conversations. Like, you visit a company's website and want to speak to support and it offers an instant chat with a bot to route your query — ChatGPT was made for doing that! That's why it has “chat” in its name. It is not a proofreading AI, it's a chat AI. If you give it input, it will generate chat, not proofreading. It will not make your post better.

You also don't want to pass your otherwise completely legitimate post through a filter that will turn it into ChatGPT output. Not only has that made your post worse, it's going to draw a target on it: you submitted a GPT output for a post and we ban those, and people are going to be looking out for GPT-ish posts to remove them. Passing a perfectly good post through ChatGPT is the best way to sabotage that post. (Or, worse yet, you'll create traps and problems for people trying to hunt down actual GPT-based misuse of the site.)

You already have perfectly adequate proofreading tools available: your own judgment and a spellcheck. You're doing well with them — keep using them and keep improving.

\$\endgroup\$
2
  • \$\begingroup\$ Mostly for cleanlyness, the digression about ChatGPT's origins has been moved to chat; feel free to continue in there (if of interest). \$\endgroup\$
    – Someone_Evil Mod
    Nov 3, 2023 at 22:29
  • 3
    \$\begingroup\$ This comment thread has gotten derailed and gotten some flags for rude/unkind messages so it has all been deleted. People who wish to continue arguing should take it to chat. \$\endgroup\$
    – Oblivious Sage Mod
    Nov 15, 2023 at 2:55
13
\$\begingroup\$

To sidestep your question for a moment, I have long believed, longer than the existence of LLMs, that you have provided some of the most consistently high quality answers on this site. I have never read one of your answers and thought “this needs some composition help”. Further, I’m pretty sure you are the top recipient of my bounties, both in reputation and number of bounties. I have an abundance of confidence that you don’t need LLM help, to the point that I’d be worried they might actually make your answers worse, at least in my opinion. Now, on to the actual question.

LLMs present a plagiarism problem for us.

I won’t reinvent the wheel here. Xirema summarizes perfectly my trouble with LLMs, reproduced below in its entirety.


I'm going to reiterate the points I made when this question was proposed at the network-wide level in a more succinct form; you can read my answer in the link if you want the long form.

Yes, ChatGPT (and other AI-generative tools) need to be banned on RPG.SE

And it's for the simple reason that these tools, at least as they exist today, are incapable of producing output that does not commit plagiarism.

There's a few criteria I would line out that I think are necessary prerequisites before they should be approved for use on this site (or any site in the Stack Exchange network), and they are

  • That the tool clearly cites every single work that was used as part of its training and ingested into its dataset
  • That every single work that was used provided explicit, specific, opt-in permission by its original author to be used as part of that specific tool and its training process
  • That the evidence of permission for each work that was used is easily accessible
  • That the tool is able to cite, in its resulting output, the works sourced that were used to generate its output.

To my knowledge, none of ChatGPT nor any other publicly available AI-generation tool is capable today of satisfying all these criterion (and it's my understanding that most-if-not-all of these tools are technologically incapable of doing so), and they should not be permitted until/unless they are developed to be able to satisfy these criterion.

\$\endgroup\$
4
  • 6
    \$\begingroup\$ I thought, and still think, this is an excessive, unrealistic, and quite possibly just plain wrong take on the topic of plagiarism. Direct copying is a problem, but unless you can and do provide just as complete an accounting of everything you've "been trained on" I don't understand your grounds for objection. \$\endgroup\$
    – Novak
    Oct 28, 2023 at 20:01
  • 3
    \$\begingroup\$ @Novak It’s very simple: a human being is socially, and legally, regarded as being capable of original creative output. That is, when a human being is “trained on” material that they learn, understand, internalize, synthesize, and recreate, they are performing an act of original creation for which they—and not the material they have trained on—deserve credit for. Academic, legal, and social understandings of credit, copyright, plagiarism, etc., recognize this. LLMs are not recognized to perform any original creation, and thus cannot be the one deserving credit: their sources are. \$\endgroup\$
    – KRyan
    Nov 1, 2023 at 20:02
  • 5
    \$\begingroup\$ @KRyan Sounds like special pleading, to me. \$\endgroup\$
    – Novak
    Nov 1, 2023 at 23:00
  • 6
    \$\begingroup\$ Yeah, this specific case makes that nonsense. In this case a human being came up with the ideas, the ordering of the arguments, etc. The LLM is serving as little more than a glorified grammar checker. I'm not seeing how the author "synthesizing" from an LLM is different from "synthesizing" from a Google result, their spell-checker, or Google Translate. \$\endgroup\$
    – AceCalhoon
    Nov 2, 2023 at 18:14
4
\$\begingroup\$

Yes, that’s fine. All critiques of plagiarism are irrelevant if you are providing an answer and having it punch up your grammar. Make sure it doesn’t change your meaning though before posting

\$\endgroup\$
1
\$\begingroup\$

I Think It's Fine For That Specific Purpose

There are two broad classes of objections to clean-up AI, that I've seen (not limited to this forum): The argument from copyright, and the argument from the virtue of labor.

To the former (copyright), I say this: What matters more is the output of the tool, than the input. No content producer has ever had the right to know whether another content producer has read their work first, or to know if they read a borrowed copy, or to demand attribution if that's the only link. That's simply not how this works, how this has ever worked, or could ever work.

What copyright law protects is concrete expressions. And while I acknowledge that the academic literature is still being written on the copyright (and, interestingly, security) implications of how LLM models work, and the possibility of direct copying from the training corpora, the risk of direct copying seems very low if you're giving it your own primary text and just asking for grammatical and stylistic clean-ups.

To the latter (virtue of labor), I have heard that argument so many times in so many ways over the course of my life that they all just blend together into an undifferentiated muddle. I collaborate on radar and satellite designs-- my work is improved, not degraded, by using calculators, spreadsheets, and numerical modeling packages. I collaborate on writing their specifications-- my work is improved, not degraded, by spellcheckers and grammar checkers.
(Ironically, but truthfully, I misspelled 'specifications' and 'misspelled' just now. I've never been able to spell 'misspelled' right on the first attempt.)

These tools, for this specific purpose are no different. Like any other tool, they need to be used wisely, for instance a minimal check to make sure the meaning hasn't been changed. But they are just tools designed to reduce the burden of certain tasks.

But Note Well: I am not in any way changing my position on the topic of using these tools to generate questions or answers wholesale. They are nowhere near reliable enough to consider that application. And when they are, people will bypass Stack Overflow entirely.

\$\endgroup\$
2
  • \$\begingroup\$ Regarding the 2nd point, I sometime think that using LLM for checking the grammar/language could be the same as asking/paying for a proof-reading of your text from people that does this for work. \$\endgroup\$
    – Eddymage
    Oct 29, 2023 at 8:00
  • \$\begingroup\$ @Eddymage I agree entirely. But there are also people who seem to look down on that. (This is a case where "not limited to this forum" is very applicable-- I see that sometimes in academic circles among native and highly fluent speakers/writers. I see it a lot more in academic circles against using LLMs for it, though.) \$\endgroup\$
    – Novak
    Oct 29, 2023 at 20:34
-2
\$\begingroup\$

What's commonly called artificial intelligence on the Internet nowadays is a method that, as with the machines it's run on, lacks will and intent. It is entirely responsive, entirely a reaction to inputs based on other inputs. It does not understand how people communicate, only the arrangements of words, because it does not have sentience.

When a real person tells you what they think somebody else is trying to say, there is interpretation founded on reason and expertise, from a person who understands that other people exist and tries to understand them. Someone who is capable of empathy because they're bought into the system of empathy as an actor in the world.

When you feed text that's lacking information into a machine, that machine can't uncover the information that's missing, it can only guess (the same way that when you feed a low-resolution photograph to a machine and ask it to upscale the photo to a larger size, it will make up elements of the image to fulfill your request, without truly having the information that would give it a better picture).

Most importantly, the machine can't be held accountable when it guesses wrong, because it isn't a being involved in the community, merely an automated service. The only person that can be held accountable is the person who decides to involve the machine in the first place.

For these reasons and more, it is less than reasonable to allow ML-parsed text to replace genuinely authored text, even in cases where a person is having difficulty expressing themself. The machine will not reduce difficulty except insofar as it suggests what's common. Sometimes that's what you need, but common text deserves no special priority on a question-and-answer site.

People will want to help you even if your command of the language you're using isn't the best.

\$\endgroup\$
1
  • \$\begingroup\$ Indeed, I did not used "artificial intelligence" for this kind of tools, since they are not "intelligent": usually, LLMs are based on statistics only. The entire field of XAI is devoted to find explanations on how and why AI models provide such outcomes, which sometimes are incredible accurate. \$\endgroup\$
    – Eddymage
    Nov 11, 2023 at 9:59

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .