Sep 2026· ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences· Vol XII-4/W2-2026, pp. 155-162· 0 citations· 11 references
TL;DR
These results should be interpreted as a comparison of graph-language interaction designs rather than a fully input-matched ablation, but they suggest that exposing task-relevant structural information is an important factor for urban spatial QA.
Abstract
Urban graphs are central to smart-city analytics, but they remain difficult for language-guided models, specifically LLMs, to use effectively in spatial question answering. This paper studies how urban graph structure can be exposed to such models through different graph-language interaction designs. We construct a controlled multi-task urban graph QA benchmark over three cities that covers adjacency count, adjacency binary, reachability, shortest path, and centrality, and compare seven mechanisms spanning compression, memory, retrieval, execution, and structural reasoning, alongside text-only and GNN-only baselines. Within this benchmark, methods using more explicit structural evidence generally outperform compression and memory-based approaches: Path Tokens reaches 78.1% average accuracy, Graph Tool 87.4%, and Counterfactual 71.7%, while centrality remains the most difficult task. These results should be interpreted as a comparison of graph-language interaction designs rather than a fully input-matched ablation, but they suggest that exposing task-relevant structural information is an important factor for urban spatial QA.
GraphDecisionBench is introduced, a model-independent benchmark that combines structural task profiles, matched graph-text input contrasts and heuristic-proposal controls to diagnose graph decision performance and illustrates the benchmark's central distinctions.
Xian-Liang Yang, Ya-Pu Zhang, Li Zhao· 0 citations
Large language models increasingly answer questions grounded in structured spatial data such as road networks: in navigation assistants, in conversational interfaces to geographic information, and in tools that maintain digital maps. Their answers are fluent but not verifiable, and in spatial domains a claim about a tu...
Kamal Essam, Ryszard S. Romaniuk· International Journal of Ele...· 1 citation
Multi-hop knowledge-graph question answering (KGQA) benchmarks are often treated as fixed language-and-reasoning tasks, but for navigation-based methods, difficulty also depends on the graph in which those tasks are instantiated. This makes graph construction a consequential but often entangled part of the navigation t...
Eduin E. Hernandez, Sergio A. Diaz, Luis F. García et al.· 0 citations
PoP-RAG is proposed, which features a passage-on-edge (PoE) graph that links the passages with graph edges to resolve the one-to-many entity-passage mapping problem and enables targeted retrieval for each sub-query and ensures transparent response derivation logic, thus enhancing explainability.
Xin-Tong Hu, Qi-Ming Zeng, Yu-Hao Lin et al.· Transactions on Graph Intell...· 1 citation
Reachability queries are a fundamental operation in large graph analysis, with applications in domains such as social networks, finance, program analysis, and XML query processing. Although many reachability indexes have been proposed, existing empirical studies remain limited in benchmark diversity, evaluation dimensi...
Huangleshuai He, Zheng-Yi Yang, Dong Wen et al.· World wide web (Bussum)· 0 citations
Conversational access to scholarly knowledge graphs promises more intuitive ways of exploring research fields, but current approaches remain limited by two major barriers: the lack of realistic multi-hop benchmarks and the brittleness of Text-to-SPARQL methods over real-world schemas. We address these gaps by introduci...
Tim Gollub, Furqan Shuja, Benno Stein· Proceedings of the 35th ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.