Fine-tuning all parameters of large language models (LLMs) necessitates substantial computational power and extended time. Latest advancements in parameter-efficient fine-tuning (PEFT) techniques, such as Adapter tuning and LoRA, allow for adjustments to only a minor fraction of the parameters of these LLMs. Concurrently, it has been noted that the issue of over-smoothing diminishes the effectiveness of these Transformer-based LLMs, resulting in suboptimal performances in downstream tasks. In this paper, we present SIBO, which is a SImple BOoster to enhance PEFT, by injecting an initial residual. SIBO is straightforward and readily extensible to a range of state-of-the-art PEFT techniques to alleviate over-smoothing and enhance performance. Extensive experiments on 22 benchmark datasets demonstrate that SIBO significantly enhances the performance of various strong baselines, achieving up to 15.7% and 23.5% improvement over existing PEFT methods on the arithmetic and commonsense reasoning tasks, respectively.

Microblogs present an excellent opportunity for monitoring and analyzing world happenings. Given that words are often ambiguous, entity linking becomes a crucial step towards understanding microblogs. In this paper, we re-examine the problem of entity linking on microblogs. We first observe that spatiotemporal (i.e., spatial and temporal) signals play a key role, but they are not utilized in existing approaches. Thus, we propose a novel entity linking framework that incorporates spatiotemporal signals through a weakly supervised process. Using entity annotations on real-world data, our experiments show that the spatiotemporal model improves F1 by more than 10 points over existing systems. Finally, we present a qualitative study to visualize the effectiveness of our approach.