Glossary · term102 of 202

LLMLingua

A prompt-compression method that reports roughly 20x token reduction at about a 1.5-point accuracy cost, measured on short-answer reasoning benchmarks rather than agent tasks.

Related terms

BBHBig-Bench Hard, a set of difficult reasoning benchmarks where compressed prompts lose little because the answer is short and reconstructable from intent.view term GSM8KA benchmark of grade-school math word problems commonly used to test reasoning accuracy under prompt compression.view term

At a glance

cited by: 1 post
categories: 1
first used: jul 2026

Appears in

Token-Compression Skills Do Not Survive MeasurementToken compression skills report savings the invoice never shows. Cache reads carry 87 percent of an agent bill, and cutting tokens can push the cost up.meta-analysis1 min

previousLibraries.io nextLongBench