Lemmy: Bestiverse
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
RSS BotBM to Hacker NewsEnglish · 54 minutes ago

Previous-Token Prediction Based LLM Inversion for Prompt Reconstruction

arxiv.org

external-link
message-square
0
link
fedilink
1
external-link

Previous-Token Prediction Based LLM Inversion for Prompt Reconstruction

arxiv.org

RSS BotBM to Hacker NewsEnglish · 54 minutes ago
message-square
0
link
fedilink
PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction
arxiv.org
external-link
Large language models (LLMs) generate text by auto-regressively sampling the next token. This inherently leads to a many-to-many mapping between prompts and responses, complicating the task of inferring prompts from observed outputs. Prior work on LLM inversion frames prompt recovery as a semantic reconstruction task. They rely on fine-tuning pretrained sequence-to-sequence models on large external datasets--and requiring access to model weights or logits--to generate semantically plausible prompts. In contrast, we present a functional approach to inverting a given LLM in a black-box setting, without auxiliary aids. We train an explicit inverse language model entirely from scratch on data synthetically generated from the target LLM itself. Analogous to forward next-token prediction, our inverse model is trained using previous-token prediction, establishing a generative link between the forward and inverse processes that enables faithful prompt reconstruction. Moreover, it naturally supports diverse prompt reconstructions through sampling, whereby all such prompts induce similar responses under the forward, target LLM. Our approach generalises across datasets and exhibits transferability in reconstructing prompts from responses generated by different LLMs. Further, across the set of token based evaluation metrics for prompt and response reconstructions, our approach outperforms prior work.

Comments

alert-triangle
You must log in or register to comment.

Hacker News

hackernews

Subscribe from Remote Instance

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !hackernews@lemmy.bestiver.se
lock
Community locked: only moderators can create posts. You can still comment on posts.

NOTICE: The bot occasionally has downtime, sorry about that. I’m working on adding better monitoring and error recovery so I can get notified faster.

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

Source of the RSS Bot.

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 300 users / day
  • 2.11K users / week
  • 4.1K users / month
  • 8.79K users / 6 months
  • 2 local subscribers
  • 5.81K subscribers
  • 65.6K Posts
  • 36.1K Comments
  • Modlog
  • mods:
  • patrick
  • RSS BotB
  • BE: 0.19.21
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org