Towards the Holographic Characteristic of LLMs for Efficient Short-text Generation

Abstract: The recent advancements in LLMs have attracted interest in exploring their in-context learning abilities and chain-of-thought capabilities. However, there are few studies investigating the specific traits related to the powerful generation capacity of LLMs. This paper aims to delve into the generation characteristics exhibited by LLMs. Through our investigation, we have discovered that LLMs tend to capture target-side keywords at the beginning of the generation process. We name this phenomenon the Holographic Characteristic of LLMs. For the purpose of exploring this characteristic and further improving the inference efficiency of LLMs, we propose a plugin called HOLO, which leverages the Holographic Characteristic to extract target-side keywords from LLMs within a limited number of generation steps and complements the sentence with a parallel lexically constrained text generation method. To verify the effectiveness of HOLO, we conduct massive experiments on LLMs of varying architectures and scales in the short-text generation scenario. The results demonstrate that HOLO achieves comparable performance to the baselines in terms of both automatic and human-like evaluation metrics and highlight the potential of the Holographic Characteristic.