Robust Transmission of Punctured Text with Large Language Model-based Recovery
This addresses the need for robust performance across datasets and tasks in semantic communication, though it appears incremental as it builds on existing LLM-based recovery methods.
The paper tackles the problem of robust text transmission in semantic communication by proposing a model that transmits only a few characters and recovers missing ones using a large language model, with simulations showing it outperforms random selection and traditional bit-based communication in low signal-to-noise ratio conditions.
With the recent advancements in deep learning, semantic communication which transmits only task-oriented features, has rapidly emerged. However, since feature extraction relies on learning-based models, its performance fundamentally depends on the training dataset or tasks. For practical scenarios, it is essential to design a model that demonstrates robust performance regardless of dataset or tasks. In this correspondence, we propose a novel text transmission model that selects and transmits only a few characters and recovers the missing characters at the receiver using a large language model (LLM). Additionally, we propose a novel importance character extractor (ICE), which selects transmitted characters to enhance LLM recovery performance. Simulations demonstrate that the proposed filter selection by ICE outperforms random filter selection, which selects transmitted characters randomly. Moreover, the proposed model exhibits robust performance across different datasets and tasks and outperforms traditional bit-based communication in low signal-to-noise ratio conditions.