Can large language models understand uncommon meanings of common words?

arXiv:2405.05741v1 Announce Type: new
Abstract: Large language models (LLMs) like ChatGPT have shown significant advancements across diverse natural language understanding (NLU) tasks, including intelligent dialogue and autonomous agents. Yet, lacking widely acknowledged testing mechanisms, answering `whether LLMs are stochastic parrots or genuinely comprehend the world' remains unclear, fostering numerous studies and sparking heated debates. Prevailing research mainly focuses on surface-level NLU, neglecting fine-grained explorations. However, such explorations are crucial for understanding their unique comprehension mechanisms, aligning with human cognition, and …

abstract agents arxiv autonomous autonomous agents chatgpt cs.ai cs.cl dialogue diverse intelligent language language models language understanding large language large language models llms natural natural language nlu stochastic studies tasks testing type understanding words world