Knowledge Base

Explore practical guides and answers by topic to understand web technologies and discover useful websites.

Answers and Guides

How LLMLingua-2 Improves on the Original LLMLingua
LLMLingua-2 improves on the original LLMLingua in three connected ways: it learns compression targets through data distillation i…
Where to Find LLMLingua Demos, Code, and Papers
The LLMLingua Series site (llmlingua.com) is the central hub for the Microsoft Research prompt-compression family: LLMLingua, Lon…
Why Compress Prompts Before Sending Them to Large Language Models?
Compress prompts before sending them to an LLM to cut inference cost and latency while keeping task performance. The need arises …
LLMLingua vs. LongLLMLingua vs. LLMLingua-2 vs. SeCom: Which Prompt Compression Method Fits Your Use Case?
The LLMLingua Series is a Microsoft Research project family for compressing prompts so that long inputs fit more efficiently into…
What Is the LLMLingua Series Website?
The LLMLingua Series site is the project home for Microsoft Research's prompt-compression work: LLMLingua, LongLLMLingua, LLMLing…