analiza aiqbench
This paper introduces SGR, a framework that enhances LLM reasoning by dynamically generating external subgraphs from knowledge graphs to provide explicit relational evidence. By combining schema-guided retrieval with Cypher-based validation, the approach significantly improves accuracy and interpretability on complex multi-step reasoning benchmarks. The key takeaway for practitioners is that integrating structured graph data with model confidence metrics offers a robust path toward addressing logical consistency and factual grounding issues.
Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation
arXiv:2606.04454v1 Announce Type: new Abstract: Large language models have shown strong performance in natural language generation and downstream reasoning tasks, but they still struggle with logical consistency, factual grounding, and interpretability in complex multi-step reasoning. To address these limitations, this paper proposes SGR, a stepwise reasoning enhancement framework that integrates large language models with external knowledge graphs through query-relevant subgraph generation. Given an input question, SGR first extracts key entities, relations, and constraints to construct a structured schema, then retrieves compact subgraphs from a knowledge graph using schema-guided querying. The generated subgraphs provide explicit relational evidence that guides the language model through step-by-step reasoning. In addition, SGR combines direct Cypher-based reasoning with collaborative reasoning integration, allowing candidate answers from multiple reasoning paths to be validated and aggregated according to both model confidence and graph consistency. Experiments on benchmark datasets including CWQ, WebQSP, GrailQA, and KQA Pro demonstrate that SGR improves reasoning accuracy and Hits@1 performance over standard prompting and several knowledge-enhanced baselines. Ablation studies further show that schema guidance and Neo4j-based retrieval are both crucial to the effectiveness of the framework. These results indicate that dynamically generated external subgraphs can improve the accuracy, robustness, and interpretability of LLM-based reasoning.
Abstract:Large language models have shown strong performance in natural language generation and downstream reasoning tasks, but they still struggle with logical consistency, factual grounding, and interpretability in complex multi-step reasoning. To address these limitations, this paper proposes SGR, a stepwise reasoning enhancement framework that integrates large language models with external knowledge graphs through query-relevant subgraph generation. Given an input question, SGR first extracts key entities, relations, and constraints to construct a structured schema, then retrieves compact subgraphs from a knowledge graph using schema-guided querying. The generated subgraphs provide explicit relational evidence that guides the language model through step-by-step reasoning. In addition, SGR combines direct Cypher-based reasoning with collaborative reasoning integration, allowing candidate answers from multiple reasoning paths to be validated and aggregated according to both model confidence and graph consistency. Experiments on benchmark datasets including CWQ, WebQSP, GrailQA, and KQA Pro demonstrate that SGR improves reasoning accuracy and Hits@1 performance over standard prompting and several knowledge-enhanced baselines. Ablation studies further show that schema guidance and Neo4j-based retrieval are both crucial to the effectiveness of the framework. These results indicate that dynamically generated external subgraphs can improve the accuracy, robustness, and interpretability of LLM-based reasoning.
Computation and Language (cs.CL)
arXiv:2606.04454 [cs.CL]
(or arXiv:2606.04454v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.04454 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 289 cuvinte
Subiecte conexe
Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning
arXiv · 22 sept. 2026
SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches
arXiv · 8 iun. 2026
Amazon is investing in the Lean Focused Research Organization
Amazon Science · 26 iul. 2026
URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER
arXiv · 22 sept. 2026