Aligning Black-Box LLMs for Aspect Sentiment Quad Prediction
Abstract: Aspect-based sentiment analysis (ABSA) focuses on extracting opinions about specific aspects, with Aspect Sentiment Quad Prediction (ASQP) being the most complex sub-task.
Large language models (LLMs) like GPT-4 exhibit strong generalization yet struggle with ASQP due to a lack of task-specific alignment.
Supervised small language models (SLMs), while effective in capturing task-specific 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 method significantly improves ASQP performance, demonstrating robustness, scalability, and potential for advancing alignment techniques in sentiment analysis.
Paper Type: Long
Research Area: Sentiment Analysis, Stylistic Analysis, and Argument Mining
Research Area Keywords: Aspect-based sentiment analysis, Aspect Sentiment Quad Prediction, Large Languge Models, In-context Learning
Contribution Types: NLP engineering experiment
Languages Studied: English
Submission Number: 900
Loading