Amit Sethi

PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction

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....