动态压缩对话上下文，让大模型长聊更稳更快
Developing Adaptive Context Compression Techniques for Large Language Models (LLMs) in Long-Running Interactions
- 根据重要性选记忆、按连贯性过滤、动态分配压缩预算
- 在多个基准上提升对话稳定性和检索准确率，减少30%以上令牌消耗
- 适合需要长期交互的AI客服、智能助手等场景
大语言模型在长时间交互中常因上下文过长导致性能下降、内存饱和和计算开销增加。本文提出一种自适应上下文压缩框架，融合重要性感知的记忆选择、连贯性敏感的过滤机制与动态预算分配策略，在控制上下文增长的同时保留关键对话信息。在LOCOMO、LOCCO和LongBench三个基准上的实验表明，该方法相比现有记忆与压缩方法，在保持对话稳定性与检索准确性的同时，显著降低令牌使用量与推理延迟。结果证明，自适应上下文压缩可在长期记忆保留与计算效率间实现有效平衡。
原文摘要 · Abstract (English)
Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression framework that integrates importance-aware memory selection, coherence-sensitive filtering, and dynamic budget allocation to retain essential conversational information while controlling context growth. The approach is evaluated on LOCOMO, LOCCO, and LongBench benchmarks to assess answer quality, retrieval accuracy, coherence preservation, and efficiency. Experimental results demonstrate that the proposed method achieves consistent improvements in conversational stability and retrieval performance while reducing token usage and inference latency compared with existing memory and compression-based approaches. These findings indicate that adaptive context compression provides an effective balance between long-term memory preservation and computational efficiency in persistent LLM interactions
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。