Aligning Black-Box LLMs for Aspect Sentiment Quad Prediction

Aspect-Based Sentiment Analysis (ABSA) focuses on extracting opinions about specific aspects, with Aspect Sentiment Quad Prediction (ASQP) being the most complex subtask. Large language models (LLMs) like GPT4 exhibit strong generalization yet struggle with ASQP due to a lack of task-specific alignment. Supervised small language models (SLMs), while effective in capturing taskspecific patterns, lack the extensive knowledge of LLMs. To address this, we propose a framework that combines SLMs and LLMs using supervised in-context learning to align LLM outputs with human preferences. One SLM is supervised to generate candidate answers and guide LLMs with task-specific instructions, while another SLM acts as a reward model iteratively evaluates and refines LLM outputs. Experiments show that our framework significantly improves ASQP performance, demonstrating robustness, scalability, and potential for advancing alignment techniques in sentiment analysis.