Study: graph serialization choice substantially affects LLM structural reasoning
The paper (arXiv:2610.22734v1) evaluates 15 graph serialization formats across nine frontier LLM configurations on ontology-based knowledge extraction and structural graph reasoning tasks. It finds knowledge extraction is relatively insensitive to format, but structural reasoning accuracy depends strongly on the serialization, with the best format varying by model, query, and task; the authors propose treating serialization as a dynamic orchestration decision.