动态筛选对话片段，让大模型更高效地处理长对话。
DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs
- 根据当前对话自动挑选相关历史片段，不依赖预设话题边界。
- 在多个长对话数据集上保持生成质量，上下文使用更精准。
- 无需训练或额外存储，适合实时长对话应用。
大型语言模型（LLMs）越来越多地用于具有频繁话题切换的长对话场景。尽管近期模型支持较长的上下文窗口，但受推理成本与延迟限制，实际应用中仍需高效管理对话历史。本文提出 DyCP，一种轻量级的外部上下文管理方法，可动态识别并检索与当前对话回合相关的对话片段，无需离线构建记忆。DyCP 在不破坏对话顺序的前提下，实现了自适应的上下文选择，无需预定义话题边界。在三个长对话基准测试（LoCoMo、MT-Bench+、SCM4LLMs）及多种 LLM 后端上，DyCP 实现了与现有方法相当的生成质量，同时显著减少上下文使用量并提升推理效率。
原文摘要 · Abstract (English)
Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts. While recent LLMs support extended context windows, efficient management of dialogue history in practice is needed due to inference cost and latency constraints. We present DyCP, a lightweight context management method implemented outside the LLM that dynamically identifies and retrieves relevant dialogue segments conditioned on the current turn, without offline memory construction. DyCP manages dialogue context while preserving the sequential nature of dialogue without predefined topic boundaries, enabling adaptive and efficient context selection. Across three long-form dialogue benchmarks-LoCoMo, MT-Bench+, and SCM4LLMs-and multiple LLM backends, DyCP achieves competitive answer quality in downstream generation, with more selective context usage and improved inference efficiency.
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。