用图结构管理对话记忆，提升长期一致性且降低计算成本。
G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agents
- 用小模型提取三元组并构建知识图谱，实现结构化记忆存储。
- 在MSC上提升响应质量9.8%，在LME上召回率提高40.8%。
- 适合需要高效长时对话的系统，如智能客服与虚拟助手。
尽管大语言模型（LLMs）推动了开放域对话系统的发展，但长期一致性仍受长上下文推理能力不足和处理大量原始文本效率低下的制约。现有方法通常依赖无结构的记忆存储（易丢失信息）或计算开销大的LLM（导致高延迟）。为此，我们提出G-Long，一个基于图增强的框架：利用微调的小语言模型（sLM）进行结构化三元组提取与关联检索，显著降低运行成本；同时引入新颖的注意力感知重要性评分机制，通过T5摘要器的交叉注意力信号识别关键记忆。在多个基准上的广泛实验表明，G-Long在响应生成与记忆检索方面均达到当前最优性能，在MSC上响应质量提升最高达9.8%，在LME上检索召回率提升40.8%，同时大幅减少计算开销。
原文摘要 · Abstract (English)
While Large Language Models (LLMs) have advanced open-domain dialogue systems, maintaining long-term consistency remains a challenge due to inherent limitations in long-context reasoning and the inefficiency of processing extensive raw text. Existing approaches typically rely on either unstructured memory storage, which is prone to information loss, or computationally expensive LLMs that incur high latency. To address these limitations, we propose G-Long, a graph-enhanced framework that utilizes a fine-tuned small Language Model (sLM) for structured triplet extraction and associative retrieval, significantly reducing operational costs. Furthermore, we introduce the novel attention-aware importance scoring mechanism that leverages the intrinsic cross-attention signals of a T5 summarizer to identify salient memories. Extensive experiments across diverse benchmarks demonstrate that G-Long achieves state-of-the-art performance in both response generation and memory retrieval, yielding performance gains of up to 9.8% in response quality on MSC and 40.8% in retrieval recall on LME, while significantly minimizing computational overhead.
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。