发表机构
Electric Power Research Institute (EPRI)（电力研究院（EPRI））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对电网模型问答的上下文预算限制，提出种子锚定图渲染方法，在固定8000字符预算下使SmallGrid数据集准确率从0.450升至0.970，效果优于LightRAG等模型且避免LLM图构建令牌。
AI 中文摘要
针对电网模型的大语言模型问答必须遵循固定的上下文预算。我们提出种子锚定图渲染，这是一种确定性方法，在共享跳数约束和上下文预算之外，无需添加特定于方法的调优参数或学习参数，可优先处理查询局部图证据。该方法提供了可验证条件，据此预定义的含答案的种子局部渲染单元会被保留在贪心的有界上下文前缀中。我们在通过通用电网模型交换标准（CGMES）交换的通用信息模型（CIM）网络模型上评估该方法。在两种受预算约束的CGMES编码中，朴素的描述优先渲染保留了所有单跳项的局部证据，但仅保留0.12和0.00的多跳项，而种子锚定渲染保留了所有此类证据。在来自SmallGrid拓扑家族的预注册100项新数据集中，在固定的8000字符上下文预算下，准确率从0.450提升至0.970。在通用检索与渲染流程中，符合标准的种子锚定图与LightRAG、Microsoft GraphRAG和HippoRAG生成的提取图表示相当或更优，同时避免了LLM图构建令牌。结果仅针对所评估的CIM/CGMES模型、阅读器和上下文预算，涉及预算约束检索而非通用问答。
英文摘要
Large language model question answering over power-grid models must respect a fixed context budget. We introduce seed-anchored graph rendering, a deterministic method that prioritizes query-local graph evidence without adding method-specific tuned or learned parameters beyond the shared hop bound and context budget. The method provides a checkable condition under which predefined seed-local answer-bearing render units are preserved in a greedy bounded-context prefix. We evaluate the approach on Common Information Model (CIM) network models exchanged through the Common Grid Model Exchange Standard (CGMES). On two budget-binding CGMES encodings, naive descriptions-first rendering retains local evidence for every single-hop item but only 0.12 and 0.00 of multi-hop items, whereas seed-anchored rendering retains all such evidence. On a preregistered fresh 100-item bank from the SmallGrid topology family, accuracy rises from 0.450 to 0.970 under a fixed 8,000-character context budget. Under a common retrieval and rendering pipeline, the standards-native seed-anchored graph matches or exceeds extracted graph representations produced by LightRAG, Microsoft GraphRAG, and HippoRAG, while avoiding LLM graph-construction tokens. The results are specific to the evaluated CIM/CGMES models, reader, and context budget; they concern budget-bounded retrieval rather than general question answering.
CommentsSubmitted to Engineering Applications of Artificial Intelligence
