Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator
This work addresses a domain-specific challenge in legal NLP for improving fairness detection in Terms of Service clauses, with incremental improvements in efficiency.
The paper tackled the problem of computationally expensive prompt optimization for fairness detection in legal text classification by proposing a framework combining Monte Carlo Tree Search with a proxy prompt evaluator, resulting in higher classification accuracy and efficiency under constrained computation budgets.
Prompt optimization aims to systematically refine prompts to enhance a language model's performance on specific tasks. Fairness detection in Terms of Service (ToS) clauses is a challenging legal NLP task that demands carefully crafted prompts to ensure reliable results. However, existing prompt optimization methods are often computationally expensive due to inefficient search strategies and costly prompt candidate scoring. In this paper, we propose a framework that combines Monte Carlo Tree Search (MCTS) with a proxy prompt evaluator to more effectively explore the prompt space while reducing evaluation costs. Experiments demonstrate that our approach achieves higher classification accuracy and efficiency than baseline methods under a constrained computation budget.