用实体图谱增强对话检索，提升长对话问答的证据覆盖率。
Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answering
- 构建实体记忆图谱，用实体关联和时间边连接对话节点。
- 在顶k=25时，证据召回率从79.7%提升至84.5%。
- 适合关注检索覆盖性、尤其是长对话问答的研究者。
实体记忆图谱将对话轮次作为原文记忆节点，通过共享实体链接重复提及的内容，并以有向时间边连接相邻记忆。查询时，检索器经由实体门控、语义融合和单跳时间恢复到密集补全路径，可保留密集余弦排序遗漏的邻近记忆。匹配的密集对照实验共享记忆与查询向量、上下文预算、答案请求协议及评估器，隔离图结构对阅读器的影响。在来自十个LoCoMo对话的1,986个问题上，图谱检索使顶k=25时的官方证据召回率从79.7468%提升至84.4842%。该召回优势在顶k=5至50范围内持续存在，但无支持的截断点显示最终答案F1有差异。四个符合论文要求的配置在GPT-3.5与DeepSeek提取器上均表现出实证鲁棒性。嵌入鲁棒性表现不一：F1未见显著对比，但召回受嵌入伪影影响敏感。该对比分离出图结构带来的检索覆盖增益，但未证明最终答案F1提升、模型或嵌入等价性，也未验证跨数据集泛化能力。
原文摘要 · Abstract (English)
Entity-Memory graph retrieval keeps dialogue turns as verbatim Memory nodes, links repeated mentions through shared Entities, and connects adjacent Memories with directed chronological edges. At query time the retriever moves from Entity gating through semantic fusion and one-hop chronological recovery to dense backfill. The path can keep a neighboring Memory that dense cosine ranking would otherwise omit. A matched dense control shares the Memory and query vectors, context budget, requested answer protocol, and evaluator, isolating graph structure from changes to the reader. On 1,986 questions from ten LoCoMo conversations, graph retrieval raises official evidence recall at top-k 25 from 79.7468% to 84.4842%. The recall advantage is supported from top-k 5 to 50, while no matched cutoff supports an overall final-answer F1 difference. Four paper-eligible requested configurations support empirical robustness across the tested GPT-3.5 and DeepSeek extractors on both outcomes. Embedding robustness is mixed: F1 has no supported contrast, but recall is sensitive to the embedding artifact. The comparison isolates a retrieval-coverage gain from graph structure. It does not establish a final-answer F1 gain, model or embedding equivalence, or cross-dataset generalization.
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。