Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG

Paper recorded by Signals 4 on 2026-09-04 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-04 on arXiv · recorded by Signals 4 on 2026-09-07

Category: cs.CL · 自然语言处理 · first seen 2026-09-07

Abstract

Retrieval-Augmented Generation (RAG) enhances language models with external knowledge, but the lengthy retrieved context inflates the input and degrades inference efficiency. Soft context compression encodes each document into a substantially shorter embedding sequence. However, most existing approaches are trained by distilling outputs from uncompressed RAG systems, inherently limiting their perf

Read on arXiv →