Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces seed-anchored graph rendering, a deterministic method designed for question answering over power-grid models that adheres to a fixed context budget. By prioritizing query-local graph evidence without the need for additional tuned parameters, the method significantly improves the retention of multi-hop evidence, achieving an accuracy increase from 0.450 to 0.970 on a 100-item test set. Evaluations show that this approach matches or surpasses existing graph representation methods while maintaining compliance with context constraints, making it particularly effective for industry-standard power-grid information models.
Seed-anchored graph rendering retains all multi-hop evidence in power-grid question answering, achieving a dramatic accuracy boost while adhering to strict context budgets.
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.