Settings

Theme

Previous-Token Prediction Based LLM Inversion for Prompt Reconstruction

arxiv.org

47 points by dalmo3 · 11 comments

Reader

3 threads
rodhruv

I don’t think it’s nearly as impressive as it is hyped to be:

They only ever evaluate on 100 prompts, and the error bars on their headline metrics are +-4-5. The headline result (65%) only applies to Qwen3-0.6B chat; for GPT-4o, it’s 11%, and for Llama-2, 17%. It’s fine-tuned on 400 ShareGPT prompts, and I suspect most of the gains are due to learning the ShareGPT prompt format. Indeed, if fine-tuned on a different dataset, it only achieves 11%.

The paper also has several misleading claims, like calling it “black-box” (needs the tokenizer) or “data-free” (only during pretraining, but see their own appendix).

henry2023

Wondering if you can input an uncensored response and then backwardly compose a prompt that effectively jailbreaks the given model.

totetsu

Imagine if you could take the AI marketing slop, or political smear campaigns, texts, and Images, and see the misanthropic sludge that was used as a prompt to generate it.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection