Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generation

About

Large Language Models (LLMs) have demonstrated strong capabilities across diverse NLP applications, such as translation, text generation, and question answering. Nevertheless, they remain limited in complex settings that demand deep reasoning and logical inference. Since these models are trained on large-scale text corpora, their generation process may still introduce irrelevant, noisy, or factually inconsistent content. To mitigate this problem, we introduce SGR, a stepwise framework that enhances LLM reasoning through external subgraph generation. SGR builds query-specific subgraphs from external knowledge bases and uses their semantic structure to support multi-step inference. By grounding intermediate reasoning steps in structured external knowledge, the framework helps the model concentrate on relevant entities, relations, and supporting evidence. In particular, SGR first constructs a subgraph tailored to the input question. It then guides the model to reason progressively over the generated structure and combines multiple reasoning trajectories to obtain the final prediction. Experimental results across several benchmark datasets show that SGR achieves consistent improvements over competitive baselines, highlighting its value for improving both reasoning accuracy and factual reliability.

Xin Zhang, Yang Cao, Baoxing Wu, Kai Song, Siying Li• 2026

Related benchmarks

TaskDatasetResultRank
Knowledge Graph Question AnsweringCWQ
Hit@163.2
212
Knowledge Graph Question AnsweringWebQSP
Hit@182.6
174
Knowledge Base Question AnsweringGrailQA
Hits@175.6
40
Showing 3 of 3 rows

Other info

Follow for update