Aspect Sentiment Quad Prediction (ASQP) aims to identify quadruples consisting of an aspect term, aspect category, opinion term, and sentiment polarity from a given sentence, which is the most representative and challenging task in aspect-based sentiment analysis. A major challenge arises when implicit sentiment is present, as existing models often confuse implicit and explicit sentiment, making it difficult to extract the quadruples effectively. To tackle this issue, we propose a framework that leverages distinct labeled features from diverse reviews and incorporates pseudo-token prompts to harness the semantic knowledge of pre-trained models, effectively capturing both implicit and explicit sentiment expressions. Our approach begins by categorizing reviews based on the presence of implicit sentiment elements. We then build new samples that combine those with implicit sentiment and those with explicit sentiment. Next, we employ prompts with pseudo-tokens to guide the model in distinguishing between implicit and explicit sentiment expressions. Extensive experimental results show that our proposed method enhances the model’s ability across four public datasets, averaging 1.99% F1 improvement, particularly in instances involving implicit sentiment. We release our code at https://github.com/chienarmor/absa-implicit.