用外部知识增强大模型，让语义解析更懂没见过的概念。
Retrieval-Augmented Semantic Parsing: Improving Generalization with Lexical Knowledge
- 将大语言模型与外部符号知识结合，提升解析能力
- 对未见过概念的识别性能接近翻倍提升
- 适合需要泛化能力的开放域语义解析场景
开放域语义解析仍是挑战性任务，神经模型常依赖启发式规则，难以处理未见概念。本文研究大语言模型在该任务中的潜力，提出检索增强语义解析（RASP），通过在解析过程中引入外部符号知识实现简单而有效的方法。实验表明，大语言模型优于以往编码器-解码器基线模型，而RASP进一步提升了其对未见概念的预测能力，在分布外概念上的性能几乎翻倍。这些发现凸显了利用大语言模型和检索机制实现鲁棒、开放域语义解析的巨大潜力。
原文摘要 · Abstract (English)
Open-domain semantic parsing remains a challenging task, as neural models often rely on heuristics and struggle to handle unseen concepts. In this paper, we investigate the potential of large language models (LLMs) for this task and introduce Retrieval-Augmented Semantic Parsing (RASP), a simple yet effective approach that integrates external symbolic knowledge into the parsing process. Our experiments not only show that LLMs outperform previous encoder-decoder baselines for semantic parsing, but that RASP further enhances their ability to predict unseen concepts, nearly doubling the performance of previous models on out-of-distribution concepts. These findings highlight the promise of leveraging large language models and retrieval mechanisms for robust and open-domain semantic parsing.
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。