measurement
The framework proposed in 'Grounding LLM Reasoning with Knowledge Graphs' achieved state-of-the-art performance on GRBench, a benchmark for domain-specific graph reasoning, with at least a 26.5% improvement over Chain-of-Thought (CoT) baselines.
Authors
Sources
- Grounding LLM Reasoning with Knowledge Graphs - arXiv arxiv.org via serper
Referenced by nodes (2)
- chain-of-thought concept
- Grounding LLM Reasoning with Knowledge Graphs concept