Proof of Unlearning for Semantic Knowledge Bases in Large Language Models-Enabled Semantic Communication

Abstract

Semantic communication is a paradigm shift in wireless systems that transmits semantic information, such as intent, context, and meaning, instead of raw data to reduce redundant data. At its core, semantic knowledge bases (SKBs) store and organize the contextual knowledge required for accurate encoding, decoding, and reasoning over semantic information. Recently, large language models (LLMs), pretrained on massive and diverse text corpora, have been integrated into SKBs to generate high-quality semantic embeddings, enable zero-shot retrieval of relevant knowledge, and support complex inference tasks across a wide range of domains. However, since the training corpus of LLM may include outdated, malicious, or privacy-sensitive content, LLM-enabled SKBs should be updated efficiently and verifiably to remove specific data without retraining from scratch. In this article, we first conduct a survey on related works and then propose a model-agnostic proof of unlearning framework for LLM-driven SKBs in semantic communications. Specifically, we track the evolution of the unlearning process by measuring drifts in the LoRA adapter subspace. We then execute successive reverse steps and generate the proof trace that a verifier can compare to provide a quantitative and verifiable unlearning guarantee. Finally, experimental results demonstrate the effectiveness of our proposed framework.