OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models

Research Summary

Contribution Summary

• We present OGD4All, a transparent, auditable, and reproducible framework based on Large Language Models (LLMs) to enhance citizens' interaction with geospatial Open Government Data (OGD).
• The system combines semantic data retrieval, agentic reasoning for iterative code generation, and secure sandboxed execution that produces verifiable multimodal outputs.
• Evaluated on a 199-question benchmark covering both factual and unanswerable questions, across 430 City-of-Zurich datasets and 11 LLMs, OGD4All reaches 98% analytical correctness and 94% recall while reliably rejecting questions unsupported

Why It Matters For Eval

• The system combines semantic data retrieval, agentic reasoning for iterative code generation, and secure sandboxed execution that produces verifiable multimodal outputs.
• Evaluated on a 199-question benchmark covering both factual and unanswerable questions, across 430 City-of-Zurich datasets and 11 LLMs, OGD4All reaches 98% analytical correctness and 94% recall while reliably rejecting questions unsupported

Related Papers

• Representation Collapse in Machine Translation Through the Lens of Angular Dispersion Embedding Neighbor
• Mechanistic Indicators of Steering Effectiveness in Large Language Models Embedding Neighbor
• ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models Embedding Neighbor
• Modality-Guided Mixture of Graph Experts with Entropy-Triggered Routing for Multimodal Recommendation Embedding Neighbor
• When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment Embedding Neighbor
• Intermittent Semi-Working Mask: A New Masking Paradigm for LLMs Embedding Neighbor
• Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework Embedding Neighbor
• DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning Embedding Neighbor
• Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning Embedding Neighbor
• Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination Tag Overlap
• Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models Tag Overlap
• EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation Tag Overlap