新研究用图结构改进长对话问答的证据召回，在LoCoMo数据集上提升近5%，但未改变最终答案质量。
Entity-Memory图检索将对话轮次作为记忆节点，通过共享实体链接重复提及，并使用有向时间边连接相邻记忆。在1,986个LoCoMo对话问题测试中，该技术将top-k 25的证据召回率从79.7468%提升至84.4842%。该优势在top-k 5到50范围内均得到支持，但未对最终答案F1分数产生显著影响。研究测试了GPT-3.5和DeepSeek提取器，验证了配置的鲁棒性。
Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answering
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.