DuanzAI: Slang-Enhanced LLM with Prompt for Humor Understanding

TL;DR

DuanzAI enhances large language models' understanding of Chinese slang and humor by integrating specialized datasets and techniques, improving AI's cultural and linguistic comprehension for more relevant responses.

Contribution

The paper introduces DuanzAI, a novel approach that significantly improves LLMs' ability to understand Chinese slang and humor through specialized datasets and advanced matching techniques.

Findings

Improved Chinese slang comprehension in LLMs

Enhanced humor understanding in AI responses

Development of ChatDAI chatbot

Abstract

Language's complexity is evident in the rich tapestry of slang expressions, often laden with humor and cultural nuances. This linguistic phenomenon has become increasingly prevalent, especially in digital communication. However, existing AI models, including ChatGPT-3.5, face challenges in comprehending these nuances, particularly in Chinese slang. In this study, we present DuanzAI, an innovative approach enhancing Large Language Models (LLMs) with deep Chinese slang comprehension. Leveraging curated datasets and advanced techniques, DuanzAI bridges the gap between human expression and AI comprehension, enabling contextually relevant responses. Our experiments contrast LLMs' performance with a custom Punchline Entity Recognition (PER) system, integrating phonetic matching and pinyin2hanzi techniques. Applying these insights, we developed ChatDAI, an advanced chatbot and released our code at \url{https://github.com/YesianRohn/DuanzAI}.