Slang Context-based Inference Enhancement via Greedy Search-Guided Chain-of-Thought Prompting

TL;DR

This paper introduces a greedy search-guided chain-of-thought prompting framework to improve slang interpretation accuracy in large language models, emphasizing the importance of structured reasoning over model size or temperature settings.

Contribution

It proposes a novel framework combining greedy search with chain-of-thought prompting specifically for slang interpretation in LLMs, addressing the challenge of contextual and cultural language understanding.

Findings

Model size and temperature have limited impact on accuracy.

Larger models do not outperform smaller ones in slang inference.

The proposed framework improves slang interpretation accuracy.

Abstract

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.