Wikipedia talk:Large language models

Chatbot to help editors improve articles

After selecting text, the control panel on the right is used to give instructions. The responses by the AI model are presented in the chat panel on the left.

I wrote a user script called WikiChatbot. It works by selecting text in an article and then clicking one of the buttons on the right to enquire about the selected text. It includes many functions. For example, it can summarize and copyedit the selected text, explain it, and provide examples. The chat panel can also be used to ask specific questions about the selected text or the topic in general. The script uses the AI model GPT 3.5. It requires an API key from OpenAI. New OpenAI accounts can use it freely for the first 3 months with certain limitations. For a more detailed description of all these issues and examples of how the script can be used, see the documentation at User:Phlsph7/WikiChatbot.

I was hoping to get some feedback on the script in general and how it may be improved. I tried to follow WP:LLM in writing the documentation of the chatbot. It would be helpful if someone could take a look to ensure that it is understandable and that the limitations and dangers are properly presented. I also added some examples of how to use edit summaries to declare LLM usage. These suggestions should be checked. Feel free to edit the documentation page directly for any minor issues. I'm also not sure how difficult it is to follow the instructions so it would be great if someone could try to set up the script, use it, and explain which steps were confusing. My OpenAI account is already older than 3 months so I was not able to verify the claims about the free period and how severe the limitations are. If someone has a younger account or is willing to open a new account to try it, that would be helpful.

Other feedback on the idea in general, on its problems, or on new features to implement is also welcome. Phlsph7 (talk) 12:45, 12 July 2023 (UTC)

I meant to reply to this sooner. This is awesome and I'm interested in this (and related ideas) related to writing / reading with ML. I'll try to have a play and give you some feedback soon. Talpedia 10:18, 17 July 2023 (UTC)

Related: see also m:ChatGPT plugin. Mathglot (talk) 07:22, 18 July 2023 (UTC)

Whilst I rather like the ability of this nifty little script to do certain things, I do have some criticism. These functions strike me as extremely risky, to the point that they should probably be disabled:

• "is it true?" - ChatGPT likely uses Wikipedia as a source, and in any case, we want verifiability, not truth. I feel quite strongly, based on several other reasons too, that this function should be disabled and never see the light of day again.
• "is it biased?" - ChatGPT lacks the ability to truly identify anything more than glaring "the brutal savages attacked the defenceless colonist family" level bias (i.e. something that any reasonably aware human should spot very quickly indeed). Best left to humans.
• "is this source reliable?" - Same as the first one, this has so much potential to go wrong that it just shouldn't exist. Sure it might tell you that Breitbart or a self-published source isn't reliable, but it may also suggest that a bad source is reliable, or at least not unreliable.

I don't think that any amount of warnings would prevent misuse or abuse of these functions, since there will always be irresponsible and incompetent people who ignore all the warnings and carry on anyway. By not giving them access to these functions, it will limit the damage that these people would cause. Doing so should not be a loss to someone who is using the tool responsibly, as the output generated by these functions would have to be checked so completely that you might as well just do it without asking the bot.

The doc page also needs a big, obvious warning bar at the top, before anything else, making it clear that use of the tool should be with considerable caution.

The doc page also doesn't comment much on the specific suitability of the bot for various tasks, as it is much more likely to stuff up when using certain functions. It should mention this, and also how it may produce incorrect responses for the different tasks. It also doesn't mention that ChatGPT doesn't give wikified responses, so wikilinks and any other formatting (bolt, italics, etc) must be added manually. The "Write new article outline" function also seems to suggest unencyclopaedic styles, with a formal "conclusion", which Wikipedia articles do not have.

Also, you will need to address the issue of WP:ENGVAR, as ChatGPT uses American English, even if the input is in a different variety of English. Mako001 (C)  (T)  🇺🇦 01:14, 23 July 2023 (UTC)

You can ask it return wikified responses and it will do it with reasonable good success rate. -- Zache (talk) 03:03, 23 July 2023 (UTC)

@Mako001 and Zache: Thanks for all the helpful ideas. I removed the buttons. I gave a short explanation at Wikipedia:Village_pump_(miscellaneous)#Feedback_on_user_script_chatbot and I'll focus here on the issues with the documentation. I implemented the warning banner and add a paragraph on the limitations of the different functions. That's a good point about the English variant being American so I mentioned that as well. I also explained that the response text needs to be wikified before it can be used in the article.

Adding a function to wikify the text directly is an interesting idea. I'll experiment a little with that. The problem is just that the script is not aware of the existing wikitext. So if asked to wikify a paragraph that already contains wikilinks then it would ignore those links. This could be confusing to editors who only want to add more links. Phlsph7 (talk) 09:12, 23 July 2023 (UTC)

I made summaries/translations/etc it so that I gave wikitext as input to chatgpt instead of plaintext. However, the problem here is how to get the wikitext from page in first place. -- Zache (talk) 09:48, 23 July 2023 (UTC)

In principle, you can already do that with the current script. To do so, go to the edit page, select the wikitext in the text area, and click one of the buttons or enter your command in chat panel of the script. I got it to add wikilinks to an existing wikitext and a translation was also possible. However, it seems to have problems with reference tags and kept removing them, even when I told it explicitly not to. I tried it for the sections Harry_Frankfurt#Personhood and Extended_modal_realism#Background, both with the same issue. Maybe this can be avoided with the right prompt. Phlsph7 (talk) 12:09, 23 July 2023 (UTC)

Thanks for setting this up. I've recently had success drafting new Wikipedia articles by feeding the text of up to 5 RS into GPT4-32k through openrouter.com/playground and simply asking it to draft the article. It does a decent job with the right prompt. You can see an example at Harrison Floyd. I'll leave more details on the talk page of User:Phlsph7/WikiChatbot, but I wanted to post here for other interested parties to join the discussion. Nowa (talk) 00:02, 20 September 2023 (UTC)

Thanks for the information. I've responded to you at Talk:Harrison_Floyd#Initial_content_summarized_from_references_using_GPT4 so that we don't have several separate discussion about the same issue. Phlsph7 (talk) 07:44, 20 September 2023 (UTC)

Ran into a brick wall I thought might be helpful to know about. I've been working on the bios of people associated with Spiritual_warfare#Spiritual_Mapping_&_the_Charismatic_movement. GPT 4 and LLama refused to read the RS claiming that it was "abusive". I can see from their point of view why that is, but nonetheless, RS is RS, so I just read it manually. Between that and the challenges of avoiding copyvios I'm a bit sour on the utility of LLMs for assisting in writing new articles. It's just easier to do it manually. Having said that, the Bing chatbot does have some utility in finding RS relative to Google. Much less crap. Nowa (talk) 00:35, 9 October 2023 (UTC)

If we're going to allow LLM editing, this is a great tool to guide editors to the specific use cases that have community approval (even if those use cases are few to none at this point). I found it to be straightforward and easy to use. –dlthewave ☎ 16:06, 23 July 2023 (UTC)

There is no policy or guideline disallowing the use of LLM or other machine learning tools. No need for any approval unless that changes. MarioGom (talk) 17:29, 11 February 2024 (UTC)

Drafts for 15,616 genes, only 9% wrong

As a demonstration of the potential for AI to impact scientific practice, we use WikiCrow to generate draft articles for the 15,616 human protein-coding genes that currently lack Wikipedia articles, or that have article stubs. WikiCrow creates articles in 8 minutes, is much more consistent than human editors at citing its sources, and makes incorrect inferences or statements about 9% of the time, a number that we expect to improve as we mature our systems.

https://www.futurehouse.org/wikicrow

Welp. Sandizer (talk) 18:41, 13 December 2023 (UTC)

Estimating risk

Raw chatgpt assist

Question to ChatGPT: "write a list of activities that can be assisted by LLMs, to write encyclopedias, in order of riskiness". ChatGPT's response appeared to have errors e.g. drafting likely more risky than language refinement, but ChatGPT said the opposite. "Assisting in the generation of citations and references" is almost halluncinatory? ChatGPT response:Sure, it's important to note that language models like GPT-3.5, often referred to as large language models (LLMs), can be powerful tools but may not always provide accurate or up-to-date information. The riskiness of using LLMs for certain activities can vary, and it's crucial to verify the information obtained from these models. Here's a list of activities related to writing encyclopedias, ordered from lower to higher perceived risk: Gathering Basic Information: Summarizing established facts and information. Compiling lists of well-known data. Creating Outlines: Generating initial outlines for encyclopedia articles. Providing structure and key points for various topics. Generating Drafts: Assisting in drafting sections of encyclopedia entries. Offering ideas and context for historical events or scientific concepts. Language Refinement: Improving the readability and coherence of drafted content. Suggesting alternative phrasing for clarity. Explaining Concepts: Providing explanations for complex concepts in simple terms. Offering background information on specific subjects. Citing Sources and References: Assisting in the generation of citations and references. Helping with proper attribution of information. Fact-Checking: Cross-referencing information with reliable sources. Verifying the accuracy of historical or scientific details. In-Depth Research Assistance: Assisting in more comprehensive research on specific topics. Offering insights into less well-known or niche subjects. Handling Controversial Topics: Providing information on controversial issues with caution. Giving balanced perspectives and highlighting multiple viewpoints. Ethical Considerations: Assessing and addressing ethical concerns in content creation. Ensuring that information presented is unbiased and fair. Up-to-Date Information: Verifying the recency of information to ensure it is current. Handling topics that may evolve rapidly with care. Legal and Sensitivity Issues: Avoiding the generation of content that may violate laws or ethical guidelines. Exercising caution when dealing with sensitive or potentially harmful topics. Remember that while LLMs can be valuable tools, they are not infallible, and human oversight is essential. Critical evaluation, fact-checking, and ensuring compliance with ethical and legal standards should always be part of the content creation process.

Grateful for corrections. This list, bot-assisted, has been revised by a human. It estimates riskiness from least to most.

• For talk pages
  • Gathering Basic Information. Summarizing established facts and information. Compiling lists of well-known data.
  • Generating outlines for articles. Providing structure and key points.
  • Offering ideas and context for historical events or scientific concepts.
  • In-Depth Research Assistance: Assisting in more comprehensive research on specific topics. Offering insights into less well-known or niche subjects.

• Main space
  • Spell-checking
  • Language Refinement: Improving readability and coherence of drafted content. Suggesting alternative phrasing for clarity. Copyedit, reformulate, simplify.
  • Explaining Concepts: Providing explanations for complex concepts in simple terms. Offering background information on specific subjects.
  • Suggest images
  • Suggest wikilinks
  • Generating summaries e.g. lead summaries or other summaries
  • Suggest expansion

• Higher risk:
  • Generating Drafts: Assisting in drafting sections of entries.
  • Fact-Checking: Cross-referencing information with reliable sources. Verifying the accuracy of historical or scientific details.
  • Up-to-Date Information: Verifying the recency of information to ensure it is current. Handling topics that may evolve rapidly with care.
  • Handling Controversial Topics: Providing information on controversial issues with caution. Giving balanced perspectives and highlighting multiple viewpoints.
  • Citing Sources and References: Assisting in the generation of citations and references. Helping with proper attribution of information.
  • Ethical Considerations: Assessing and addressing ethical concerns in content creation. Ensuring that information presented is unbiased and fair.
  • Legal and Sensitivity Issues

Tom B (talk) 16:23, 20 December 2023 (UTC)

Discussion at Wikipedia talk:WikiProject AI Cleanup § Proposal: adopting WP:LLM as this WikiProject's WP:ADVICEPAGE

 You are invited to join the discussion at Wikipedia talk:WikiProject AI Cleanup § Proposal: adopting WP:LLM as this WikiProject's WP:ADVICEPAGE. ^Queenof_Hearts 21:37, 9 January 2024 (UTC)

Someone implemented a full-on article generator, and Anthropic gave it an award

Blog post description, GitHub repo, based on this Stanford work, which also has a repo, and a live working demo.

Have people noticed those kind of articles? The outline structure is more distinctive and flamboyant than we usually see from human editors. 141.239.252.245 (talk) 05:43, 26 April 2024 (UTC)