Better Handling Coreference Resolution in Aspect Level Sentiment Classification by Fine-Tuning Language Models
This work addresses a specific bottleneck in automated customer feedback analysis for companies, but it is incremental as it builds on existing LLM methods.
The paper tackles the problem of poor performance of Large Language Models in Aspect Level Sentiment Classification when Coreference Resolution is required, by fine-tuning on inferential tasks, resulting in improved model ability as evidenced by performance gains.
Customer feedback is invaluable to companies as they refine their products. Monitoring customer feedback can be automated with Aspect Level Sentiment Classification (ALSC) which allows us to analyse specific aspects of the products in reviews. Large Language Models (LLMs) are the heart of many state-of-the-art ALSC solutions, but they perform poorly in some scenarios requiring Coreference Resolution (CR). In this work, we propose a framework to improve an LLM's performance on CR-containing reviews by fine tuning on highly inferential tasks. We show that the performance improvement is likely attributed to the improved model CR ability. We also release a new dataset that focuses on CR in ALSC.