Slang Context-based Inference Enhancement via Greedy Search-Guided Chain-of-Thought Prompting
For NLP researchers and practitioners, this work offers a practical method to enhance slang comprehension in small models, though the gains are incremental.
The paper investigates slang interpretation in LLMs and proposes a greedy search-guided chain-of-thought prompting framework that improves accuracy for small language models, showing that model size and temperature have limited impact.
Slang interpretation has been a challenging downstream task for Large Language Models (LLMs) as the expressions are inherently embedded in contextual, cultural, and linguistic frameworks. In the absence of domain-specific training data, it is difficult for LLMs to accurately interpret slang meaning based on lexical information. This paper attempts to investigate the challenges of slang inference using large LLMs and presents a greedy search-guided chain-of-thought framework for slang interpretation. Through our experiments, we conclude that the model size and temperature settings have limited impact on inference accuracy. Transformer-based models with larger active parameters do not generate higher accuracy than smaller models. Based on the results of the above empirical study, we integrate greedy search algorithms with chain-of-thought prompting for small language models to build a framework that improves the accuracy of slang interpretation. The experimental results indicate that our proposed framework demonstrates improved accuracy in slang meaning interpretation. These findings contribute to the understanding of context dependency in language models and provide a practical solution for enhancing slang comprehension through a structured reasoning prompting framework.