QwenLong-CPRS is a 7B instruction-guided compressor that shrinks long contexts to query-relevant spans, boosting downstream LLM accuracy and cutting prefill cost.
Claude 3.7 sonnet
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
QwenLong-CPRS: Towards $\infty$-LLMs with Dynamic Context Optimization
QwenLong-CPRS is a 7B instruction-guided compressor that shrinks long contexts to query-relevant spans, boosting downstream LLM accuracy and cutting prefill cost.