Exploring the Performance of Large Language Models on Subjective Span Identification Tasks
This work addresses the underexplored problem of subjective span identification with LLMs for NLP researchers, but it is incremental as it extends existing methods to new tasks.
The paper evaluated the performance of large language models (LLMs) on subjective span identification tasks, such as sentiment analysis and claim verification, using strategies like instruction tuning and in-context learning, and found that underlying text relationships help LLMs identify precise spans.
Identifying relevant text spans is important for several downstream tasks in NLP, as it contributes to model explainability. While most span identification approaches rely on relatively smaller pre-trained language models like BERT, a few recent approaches have leveraged the latest generation of Large Language Models (LLMs) for the task. Current work has focused on explicit span identification like Named Entity Recognition (NER), while more subjective span identification with LLMs in tasks like Aspect-based Sentiment Analysis (ABSA) has been underexplored. In this paper, we fill this important gap by presenting an evaluation of the performance of various LLMs on text span identification in three popular tasks, namely sentiment analysis, offensive language identification, and claim verification. We explore several LLM strategies like instruction tuning, in-context learning, and chain of thought. Our results indicate underlying relationships within text aid LLMs in identifying precise text spans.