Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Hyunji, Li, Kevin Chenhao, Grabmair, Matthias, Xu, Shanshan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.08524
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915542628040704
author Lee, Hyunji
Li, Kevin Chenhao
Grabmair, Matthias
Xu, Shanshan
author_facet Lee, Hyunji
Li, Kevin Chenhao
Grabmair, Matthias
Xu, Shanshan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08524
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator
Lee, Hyunji
Li, Kevin Chenhao
Grabmair, Matthias
Xu, Shanshan
Computation and Language
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.
title Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator
topic Computation and Language
url https://arxiv.org/abs/2510.08524