arXiv NLP
techCenter
Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressorstranslating…
1 min readUnknownarXiv Press Group
arXiv:2608.26175v1 Announce Type: new
Abstract: Extractive prompt compression promises to cut LLM inference costs by removing low-information tokens, and learned compressors such as LLMLingua-2 report strong results on English benchmarks. Most other languages already pay a…