LLM-based Discriminative Reasoning for Knowledge Graph Question Answering

2024/12/17 by Mingze Xu, Xu, Mufan, Kehai Chen +9 · 3 citations
Computer Science · #Advanced Graph Neural Networks #Cognitive Computing and Networks #Computation and Language (cs.CL) #FOS: Computer and information sciences #Semantic Web and Ontologies

paper · pdf · doi:10.48550/arxiv.2412.12643

openalex publication_date 2024/12/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Large language models (LLMs) based on generative pre-trained Transformer have achieved remarkable performance on knowledge graph question-answering (KGQA) tasks. However, LLMs often produce ungrounded subgraph planning or reasoning results in KGQA due to the hallucinatory behavior brought by the generative paradigm. To tackle this issue, we propose READS to reformulate the KGQA process into discriminative subtasks, which simplifies the search space for each subtasks. Based on the subtasks, we design a new corresponding discriminative inference strategy to conduct the reasoning for KGQA, thereby alleviating hallucination and ungrounded reasoning issues in LLMs. Experimental results show that the proposed approach outperforms multiple strong comparison methods, along with achieving state-of-the-art performance on widely used benchmarks WebQSP and CWQ.

Cited by

• DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS
• Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking
• Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning

Related

• RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
• Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models
• KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
• Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning
• Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering