Network-based Spatial Context Retrieval for Open-weight LLMs: A Faithfulness Benchmark for Grounded Geographic Reasoning
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/perezjoan/NSCR-LLM
Terminology
Sources
- Gemma 3 Technical Report
- The Llama 3 Herd of Models
- The Curious Case of Neural Text Degeneration
- Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models
- CTRL: A Conditional Transformer Language Model for Controllable Generation
- Autonomous GIS: the next-generation AI-powered GIS
- GeoLLM: Extracting Geospatial Knowledge from Large Language Models
- Large Language Models are Geographically Biased
- Chatmap : Large Language Model Interaction with Cartographic Data
- ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence
- Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
- Qwen3 Technical Report
- Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions
- GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks