Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs
CoRR(2024)
摘要
In this paper, we explore a new way for user targeting, where non-expert
marketers could select their target users solely given demands in natural
language form. The key to this issue is how to transform natural languages into
practical structured logical languages, i.e., the structured understanding of
marketer demands. Considering the impressive natural language processing
ability of large language models (LLMs), we try to leverage LLMs to solve this
issue. Past research indicates that the reasoning ability of LLMs can be
effectively enhanced through chain-of-thought (CoT) prompting. But existing
methods still have some limitations: (1) Previous methods either use simple
"Let's think step by step" spells or provide fixed examples in demonstrations
without considering compatibility between prompts and questions, making LLMs
ineffective in some complex reasoning tasks such as structured language
transformation. (2) Previous methods are often implemented in closed-source
models or excessively large models, which is not suitable in industrial
practical scenarios. Based on these, we propose ARALLM (i.e., Analogical
Reasoning Augmented Large Language Models) consisting of two modules:
Analogical Reasoning based Prompting and Reasoning-Augmented Multi-Task Model
Distillation.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要