SLANG: New Concept Comprehension of Large Language Models

The dynamic nature of language, particularly evident in the realm of slang and memes on the Internet, poses serious challenges to the adaptability of large language models (LLMs). Traditionally anchored to static datasets, these models often struggle to keep up with the rapid linguistic evolution characteristic of online communities. This research addresses the critical need to bridge this gap, aiming to enhance LLMs' comprehension of the evolving new concepts on the internet, without the high cost of continual retraining. To address this issue, we propose a new benchmark $\textbf{SLANG}$, which can autonomously integrates novel data to stay dataset up-to-date, to assess LLMs' capability in comprehending emerging concepts and an approach $\textbf{FOCUS}$, which uses causal inference to enhance LLMs to understand new phrases and their colloquial context. This benchmark and approach involves digesting real-world instances of linguistic shifts, serving as contextual beacons, to form more precise and contextually relevant connections between newly emerging expressions and their intended meanings. The empirical analysis shows that our causal inference-based approach outperforms the traditional models in terms of precision and relevance in the interpretation of internet slang and memes.