paper-with-me

Papers

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

2026-05-15 · Xin Zhang, Yang Cao, Baoxing Wu, Kai Song, Siying Li arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.16117

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringText Generation

Similar Papers 제목 키워드 기반

A Stepwise-Enhanced Reasoning Framework for Large Language Models Based on External Subgraph Generation

2025-12-29 · Xin Zhang, Yang Cao, Baoxing Wu, Xinyi Chen 외 arxiv

Large Language Models (LLMs) have achieved strong performance across a wide range of natural language processing tasks in recent years, including machine translation, text generation, and question answering. As their app…

Machine TranslationQuestion AnsweringText Generation

Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation

2026-06-03 · Xin Zhang, Yang Cao, Baoxing Wu, Kai Song 외 arxiv

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 mult…

Knowledge Graphs

Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision

2025-10-01 · Ge Chang, Jinbo Su, Jiacheng Liu, Pengfei Yang 외 arxiv

Integrating textual graphs into Large Language Models (LLMs) is promising for complex graph-based QA. However, a key bottleneck is retrieving informative yet compact subgraphs that fit the LLM context. Existing retriever…

Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution

2026-05-19 · Xiaoou Liu, Tiejin Chen, Dengjia Zhang, Yaqing Wang 외 arxiv

Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning trace might fail remains difficult. Confi…

Multi-hop Question AnsweringMathematical Reasoning

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning

2026-05-13 · Junjie Zhang, Guozheng Ma, Shunyu Liu, Zetian Hu 외 arxiv

Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs). However, existing step-level efforts suffer from costly annotations …

Reinforcement Learning