Large language models (LLMs) have demonstrated remarkable capabilities in pushing the boundaries of natural language understanding. Nevertheless, the majority of existing open-source LLMs still fall short of meeting satisfactory standards when it comes to addressing numerical problems, especially as the enhancement of their numerical capabilities heavily relies on extensive data.To bridge the gap, we aim to improve the numerical understanding of LLMs by means of efficient data alignment, utilizing only a limited amount of necessary data.Specifically, we first use a data discovery strategy to obtain the most effective portion of numerical data from large datasets. Then, self-augmentation is performed to maximize the potential of the training data. Thirdly, answers of all traning samples are aligned based on some simple rules. Finally, our method achieves the first place in the competition, offering new insights and methodologies for numerical understanding research in LLMs.

Emotion classification on code-mixed text messages is challenging due to the multilingual languages and non-literal cues (i.e., emoticons). To solve these problems, we propose an innovative soft prompt tuning method, which is lightweight and effective to release potential abilities of the pre-trained language models and improve the classification results. Firstly, we transform emoticons into textual information to utilize their rich emotional information. Then, variety of innovative templates and verbalizers are applied to promote emotion classification. Extensive experiments show that transforming emoticons and employing prompt tuning both benefit the performance. Finally, as a part of WASSA 2023, we obtain the accuracy of 0.972 in track MLEC and 0.892 in track MCEC, yielding the second place in both two tracks.