Can LLMs be used in reverse?

When you use an AI model, the chat is just one long continuous string. LLMs are only trained to generate what comes after a special token like <assistant_start>, and they get stopped when it's the user's turn to type.

So, what happens if we don't stop them and we let them write the user message? (no finetuning allowed, obviously!)

Chat with reversed model Tell me more! (scroll down)

Models read a single big block of text, where special tokens mark which messages come from the assistant and which come from the user.

When you send a message, it gets wrapped between tokens like <user_start> and <user_end>. The assistant, on the other hand, keeps generating until it produces something like <assistant_end>, which stops it so that you (the user) can finally send another message.

So, we can just use the template in reverse. After <assistant_end>, we add <user_start> and let the model generate from there, so it writes the user message.

I also wanted to test the other obvious way to simulate human messages: simply asking the model to "be human". So there are two configurations: native, which uses the chat template in reverse, and roleplay.

After some testing I chose GPT 6 Astra as a judge (see ). Astra sees the chat so far and two replies, the real one and the AI one, and has to say which one the person wrote (each pair is shown in both orders). A model's score is how often it fools the judge: 50% means the judge can't tell. I also made a quick test so you can try to be the judge →

So, finally, here are the results! It's clear that no model comes close to emulating humans well, not even UserLM, which was trained to do exactly that. It's also clear that native is much better than roleplay in pretty much all the tested models. Also, notice the difference in scores between follow-ups and first messages: it's much easier for models to perform well in the former (as expected).

Bigger models are not better at fooling the judge, the family a model comes from matters much more.

Native mode keeps messages varied. Real people opened the conversations in , and models in native mode are surprisingly varied in their openings too. Roleplay on the other hand has just a handful of openings that get recycled.

Here, each square is a conversation: stronger shades mean more models fooled the judge in both orders. Click on the squares to see the details.

Bonus! Some of the messages the models wrote were .