作者位次 #2/4ACL 2026Poster· Natural Language Processing
Bridging the Memorization-Utilization Gap: Near-Lossless Context Compression via Reinforcement Learning
Yujan Ting · Xu Tang · Terrence Chen · Weijing Huang
摘要
Despite recent progress in context compression, we identify a fundamental memorization-utilization gap where models can compress context with near-perfect fidelity yet fail to effectively utilize these compressed representations for downstream tasks. We address this with a holistic training parad...