Wireless signals lost in heavy static can now be recovered by an AI that guesses the words based on their meaning.
April 24, 2026
Original Paper
LLM-Viterbi: Semantic-Aware Decoding for Convolutional Codes
arXiv · 2604.19035
The Takeaway
Old-school error correction relies on mathematical codes to fix corrupted data packets. When noise levels get too high, these math formulas simply fail and the message is lost. This system integrates a language model directly into the decoding process to fill in the blanks. It uses linguistic probability to predict what a person likely said when the signal is too garbled for traditional logic. This approach allows communication to continue in extreme environments where radio signals were previously unusable.
From the abstract
Traditional wireless communications rely solely on bit-level channel coding for error correction, without exploiting the inherent linguistic structure of the data source. This paper proposes a large language model (LLM) Viterbi decoder that integrates LLM priors into the Viterbi decoding for text transmission over AWGN channels. The proposed decoder maintains multiple candidate paths during the Viterbi decoding and periodically evaluates path reliabilities using a fine-tuned Byte-level T5 (ByT5)