There is a non-trivial chance that the LLM would've added a link to _something_, but links/references seem like a very common thing to hallucinate, no?
The way around that is that is for LLM-based tools to run a regular search engine query in the background and feed the results of that in alongside the prompt. (Usually a two-step process of the LLM formulating the query, then another pass on the results)
The used results can then have their link either added to the end result separately, guaranteeing it is correct, or added to the prompt and "telling the LLM to include it", which retains a risk of hallucination, yes.
Common to both of these is the failure mode that the LLM can still hallucinate whilst "summarizing" the results, meaning you still have no guarantee that the claims made actually show up in the results.
> The way around that is that is for LLM-based tools to run a regular search engine query in the background and feed the results of that in alongside the prompt. (Usually a two-step process of the LLM formulating the query, then another pass on the results)
Would the LLM-based tool be able to determine that the top results are just SEO-spam sites and move lower in the list, or just accept the spam results as gospel?
The practical and readily-observable-from-output answer is "No, they cannot meaningfully identify spam or misinformation, and do indeed just accept the results as gospel"; Google's AI summary works this way and is repeatedly wrong in exactly this way. Google's repeatedly had it be wrong even in the adcopy.
The theoretical mechanism is that the attention mechanism with LLMs would be able to select which parts of the results are fed further into the results. This is how the model is capable of finding parts of the text that are "relevant". The problem is that this just isn't enough to robustly identify spam or incorrect information.
However, we can isolate this "find the relevant bit" functionality away from the rest of the LLM to enhance regular search engines. It's hard to say how useful this is; Google has intentionally damaged their search engine and it may simply not be worth the GPU cycles compared to traditional approaches, but it's an idea being widely explored right now.
>The way around that is that is for LLM-based tools to run a regular search engine query in the background and feed the results of that in alongside the prompt.
Hardly better, as soon those "search engine results" would be AI slop themselves, including actual published papers (phoned-in by using AI, and "peer reviewed" by using AI from indifferent reviewers)
Happens frequently still with GTP 4o (and now 5) and Claude. Makes up "biographies" unrelated to the actual people, gives me bullshit non-existing API options and cli flags, etc.
And then on the rare occasion they do link to a chat, their prompt is something like:
"Tell about a person of history who was important for their work inthe time of their existence and give quotes of what they said that made them important when they were speaking include notes and other stories about them and give details about their life who they married and their kids and who their parents were and other big things they did do in their lives"
It feels so common actually that I would not even bother sharing them. ChatGPT gives me hallucinated URLs all... the... time. Like several times a day. You can fix it by prompting it to Google the subject or research it otherwise it just vomits garbage.
LLMs are not databases, they are text processors that need to be trained on ungodly amounts of data and can sort of kind of double as a database, though a very fallible one. Inject ground truth and you're cooking; don't and it's a crap shoot. (not saying anything new here, but it bears repeating).
P. Give me quotes from Aristophanes describing the Peloponesian war as unfortunate.
A. Yes — Aristophanes, the Athenian comic playwright, lived through almost the entire Peloponnesian War (431–404 BCE) and his plays are full of bitter humor about Greeks destroying each other. He often portrays it as an unfortunate, fratricidal conflict.
Here are a few key passages (in translation):
Acharnians (425 BCE)
Written during the war’s early years, it shows a farmer sick of the fighting:
• Dicaeopolis (the main character) laments:
“This war, which has come upon us all, is nothing but Greeks fighting Greeks.”
He later makes a private peace treaty with Sparta for himself, mocking the idea that the wider war must continue when ordinary people suffer.
Peace (421 BCE)
Produced right before the “Peace of Nicias”:
• Trygaeus, the hero, flies up to heaven to free the goddess Peace:
“It is monstrous that Greeks should destroy one another, while barbarians stand by laughing.”
This captures Aristophanes’ view that the war was not only ruinous but also shameful, as it weakened Greece before foreign enemies.
In sum: Aristophanes consistently portrayed the Peloponnesian War as a tragic absurdity — Greeks killing Greeks while the true enemies (Persians/“barbarians”) watched and benefitted. His comedies combine satire with a deep sense that the conflict was fratricidal and unnecessary.
P. You said Dicaeopolis (the main character) laments: “This war, which has come upon us all, is nothing but Greeks fighting Greeks.” Where is that quote?
A. Good catch — let’s pin this down carefully.
In Aristophanes’ Acharnians (425 BCE), the character Dicaeopolis indeed complains that the Peloponnesian War is a fratricidal war among Greeks, but the exact wording depends on the translation.
⸻
Where it appears
• Early in the play (lines ~100–120), Dicaeopolis is waiting for the Assembly to begin. He grumbles about the war, saying essentially that it is:
“A war of Greek against Greek, when we should be standing united against the barbarians.”
⸻
Examples from published translations
• Benjamin Rogers (1924 translation):
“I am heartily tired of these Grecian wars, of Greeks fighting against Greeks.”
• Alan H. Sommerstein (Loeb Classical Library, 2002): (lines 116–118) “It’s not right — Greeks at war with Greeks, while the barbarian looks on, laughing at us.”
----
Needless to say, that quote is nowhere in the Acharnians - nor anything roughly equivalent. Not only that, in the later response it attributes to the play "Acharnians" the quote it initially attributed to the play "Peace".
There is a non-trivial chance that the LLM would've added a link to _something_, but links/references seem like a very common thing to hallucinate, no?