实体记忆图检索提升长对话问答中的证据覆盖率
Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answering
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出实体记忆图检索方法，在10个LoCoMo对话的1986个问题上，使top-k=25的证据召回率提升约4.74个百分点，实现检索覆盖增益。
AI中文摘要：
实体记忆图检索将对话轮次作为逐字记忆节点，通过共享实体链接重复提及内容，并以有向时间边连接相邻记忆。检索时，检索器从实体门控经语义融合、单跳时间恢复到密集回填，该路径可保留密集余弦排序会遗漏的相邻记忆。匹配的密集控制方法共享记忆与查询向量、上下文预算、请求答案协议及评估器，从而将图结构与阅读器的改动隔离开。在来自10个LoCoMo对话的1986个问题上，图检索使top-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top-k=5到50区间均成立，且无匹配截断导致整体最终答案F1值出现差异。四种符合论文要求的配置在测试的GPT-3.5和DeepSeek提取器上，于两项指标均展现出经验鲁棒性；嵌入鲁棒性则参差不齐：F1值无支持性对比，但召回率对嵌入伪影敏感。该对比分离出图结构带来的检索覆盖增益，但未确立最终答案F1增益、模型或嵌入等价性，也未验证跨数据集泛化能力。
英文摘要：
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.
