用判别式推理减少大模型在知识图谱问答中的幻觉
LLM-based Discriminative Reasoning for Knowledge Graph Question Answering
- 将问答任务拆解为可判别的小任务，缩小搜索空间
- 在WebQSP和CWQ上达到当前最佳性能
- 适合需要可靠推理的KGQA应用
基于生成式预训练变换器的大语言模型在知识图谱问答（KGQA）任务中表现优异。然而，由于生成范式带来的幻觉行为，大模型常产生无依据的子图规划或推理结果。为此，我们提出READS，将KGQA过程重构为判别式子任务，简化每个子任务的搜索空间。基于这些子任务，设计新的判别式推理策略，实现对KGQA的推理，从而缓解大模型的幻觉与无依据推理问题。实验表明，该方法优于多个强基线模型，在广泛使用的WebQSP和CWQ基准上达到当前最优性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。