Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios
This addresses efficiency and accuracy issues for users of LLMs in long-context applications, though it appears incremental as it builds on existing compression methods.
The paper tackles the problem of redundant information and sensitivity to key information placement in long-context scenarios for large language models by introducing Perception Compressor, a training-free prompt compression framework, which achieves state-of-the-art performance on benchmarks like NaturalQuestions, LongBench, and MuSiQue.
Large language models (LLMs) demonstrate exceptional capabilities in various scenarios. However, they suffer from much redundant information and are sensitive to the position of key information in long context scenarios. To address these challenges, we present Perception Compressor, a training-free prompt compression framework. It includes a perception retriever that leverages guiding questions and instruction to retrieve the most relevant demonstrations, a dual-slope ratio allocator to dynamically allocate compression ratios and open-book ratios, and a semi-guided iterative compression that retains key information at the token level while removing tokens that distract the LLM. We conduct extensive experiments on long context benchmarks, i.e., NaturalQuestions, LongBench, and MuSiQue. Experiment results show that Perception Compressor outperforms existing methods by a large margin, achieving state-of-the-art performance.