Using an LLM as a next-token predictor with arithmetic coding compresses LLM-generated text about 20x, roughly 4 to 7 times better than Gzip, LZMA, or neural compressors in the paper's benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction
Using an LLM as a next-token predictor with arithmetic coding compresses LLM-generated text about 20x, roughly 4 to 7 times better than Gzip, LZMA, or neural compressors in the paper's benchmarks.