Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Emergent retokenization symmetry in large language models: phenomenology and applications
Kanishk Jain, Matthew Day, Tankut Can
Tokenization introduces representational redundancy: under a fixed token vocabulary, every byte string admits many valid token encodings, or segmentations, that decode to the same…
cs.CL2026
Semantic Chunking and the Entropy of Natural Language
Weishun Zhong, Doron Sivan, Tankut Can +2
Humans and large language models can predict next letter or word from its prior context much better than random guessing, indicating strong redundancy of language viewed as a stoch…