给大模型加语义提示，能有效提升其表现
Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints
- 将语义提示嵌入提示词，而非直接输入解析结果
- 在多个任务上显著提升大模型性能
- 适合希望优化大模型推理能力的研究者
语义解析旨在捕捉句子含义并转化为逻辑结构化形式。以往研究显示，语义解析可提升小型模型（如BERT）在下游任务中的表现。然而，这种提升是否适用于大语言模型（LLM）尚不明确。本文实证发现，与小型模型不同，直接将语义解析结果引入大模型反而会降低其性能。为此，我们提出SENSE——一种新型提示方法，将语义提示嵌入提示词中。实验表明，SENSE在多个任务上一致提升了大模型性能，凸显了融入语义信息以增强大模型能力的潜力。
原文摘要 · Abstract (English)
Semantic Parsing aims to capture the meaning of a sentence and convert it into a logical, structured form. Previous studies show that semantic parsing enhances the performance of smaller models (e.g., BERT) on downstream tasks. However, it remains unclear whether the improvements extend similarly to LLMs. In this paper, our empirical findings reveal that, unlike smaller models, directly adding semantic parsing results into LLMs reduces their performance. To overcome this, we propose SENSE, a novel prompting approach that embeds semantic hints within the prompt. Experiments show that SENSE consistently improves LLMs' performance across various tasks, highlighting the potential of integrating semantic information to improve LLM capabilities.
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。