Real-Time Text Transmission via LLM-Based Entropy Coding over Fixed-Rate Channels
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915976397717504 |
|---|---|
| author | Kunde, Vishnu Teja Chamberland, Jean-Francois Narayanan, Krishna R. Ebert, Jamison |
| author_facet | Kunde, Vishnu Teja Chamberland, Jean-Francois Narayanan, Krishna R. Ebert, Jamison |
| contents | Learning, prediction, and compression are intimately connected: a model that accurately predicts the next symbol in a sequence can be coupled with a source coder to compress that sequence near its information-theoretic limit. When tokenized characters arriving at a fixed reading pace are encoded into variable-length codewords and streamed over a fixed-rate channel, a queue forms whose per-token delay depends on the mean and variance of the bit lengths and on the coder's algorithmic latency. This paper investigates the compression--delay tradeoff that arises when a causal language model serves as the sequential predictor within a predict-then-code architecture for real-time text transmission. Several coding schemes are compared: Shannon (ideal), Huffman, arithmetic coding, rANS at various block sizes, and gzip. The analysis separates algorithmic delay, inherent to the coder, from computational delay, which shrinks as hardware improves. Huffman is the practical choice for over-provisioned channels, with zero algorithmic delay and modest compression overhead. Arithmetic coding achieves near-optimal compression at the cost of decodability delay. Findings are validated across two scales: GPT-2 (124M) and Llama~3.2 (3B), a twenty-five-fold parameter range. This scaling yields an approximately 38\% reduction in bits per character, effectively over-provisioning the channel and thereby changing which coder is optimal. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01991 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Real-Time Text Transmission via LLM-Based Entropy Coding over Fixed-Rate Channels Kunde, Vishnu Teja Chamberland, Jean-Francois Narayanan, Krishna R. Ebert, Jamison Information Theory Machine Learning Learning, prediction, and compression are intimately connected: a model that accurately predicts the next symbol in a sequence can be coupled with a source coder to compress that sequence near its information-theoretic limit. When tokenized characters arriving at a fixed reading pace are encoded into variable-length codewords and streamed over a fixed-rate channel, a queue forms whose per-token delay depends on the mean and variance of the bit lengths and on the coder's algorithmic latency. This paper investigates the compression--delay tradeoff that arises when a causal language model serves as the sequential predictor within a predict-then-code architecture for real-time text transmission. Several coding schemes are compared: Shannon (ideal), Huffman, arithmetic coding, rANS at various block sizes, and gzip. The analysis separates algorithmic delay, inherent to the coder, from computational delay, which shrinks as hardware improves. Huffman is the practical choice for over-provisioned channels, with zero algorithmic delay and modest compression overhead. Arithmetic coding achieves near-optimal compression at the cost of decodability delay. Findings are validated across two scales: GPT-2 (124M) and Llama~3.2 (3B), a twenty-five-fold parameter range. This scaling yields an approximately 38\% reduction in bits per character, effectively over-provisioning the channel and thereby changing which coder is optimal. |
| title | Real-Time Text Transmission via LLM-Based Entropy Coding over Fixed-Rate Channels |
| topic | Information Theory Machine Learning |
| url | https://arxiv.org/abs/2605.01991 |