Strategic deletion strategies paired with LLM reconstruction enable lossy semantic text compression, where word-frequency deletion serves as a competitive low-cost baseline across retention rates on news data.
Entropy and Hybrid rows use GPT-2 surprisal (same pipeline as BBC News experiments)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction
Strategic deletion strategies paired with LLM reconstruction enable lossy semantic text compression, where word-frequency deletion serves as a competitive low-cost baseline across retention rates on news data.