Grounding LLM Reasoning with Knowledge Graphs ↔ chain-of-thought

Relations (1)

related 2.00 — strongly supporting 3 facts

The concept 'chain-of-thought' is a core reasoning strategy integrated into the framework described in 'Grounding LLM Reasoning with Knowledge Graphs' [1], [2], and serves as a baseline for measuring the framework's performance improvements [3].

Facts (3)

Sources

Grounding LLM Reasoning with Knowledge Graphs - arXiv arxiv.org arXiv 3 facts

claimThe framework proposed in 'Grounding LLM Reasoning with Knowledge Graphs' incorporates multiple reasoning strategies, specifically Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT).

measurementThe 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.

procedureThe method in 'Grounding LLM Reasoning with Knowledge Graphs' combines reasoning strategies (Chain-of-Thought, Tree-of-Thought, Graph-of-Thought) with two graph interaction methods: an agent to navigate the graph, and an automatic graph exploration mechanism based on generated text.