# Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator

arXiv: https://arxiv.org/abs/2510.08524 · HTML: https://mlsanity.com/paper/2510.08524/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization](https://mlsanity.com/paper/2310.16427/) (2023)
- [Does Prompt Formatting Have Any Impact on LLM Performance?](https://mlsanity.com/paper/2411.10541/) (2024)
- [The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance](https://mlsanity.com/paper/2401.03729/) (2024)
- [CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Service](https://mlsanity.com/paper/1805.01217/) (2018)
- [Efficient multi-prompt evaluation of LLMs](https://mlsanity.com/paper/2405.17202/) (2024)
- [Self-Supervised Prompt Optimization](https://mlsanity.com/paper/2502.06855/) (2025)
- [System Prompt Optimization with Meta-Learning](https://mlsanity.com/paper/2505.09666/) (2025)
- [Fast Proxies for LLM Robustness Evaluation](https://mlsanity.com/paper/2502.10487/) (2025)
- [Attack on Unfair ToS Clause Detection: A Case Study using Universal Adversarial Triggers](https://mlsanity.com/paper/2211.15556/) (2022)

## Built on by (most cited first, 2 of 2)

- [Learning Transferable Topology Priors for Multi-Agent LLM Collaboration Across Domains](https://mlsanity.com/paper/2605.17359/) (2026)
- [Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free](https://mlsanity.com/paper/2605.16767/) (2026)

## Abstract (arXiv)

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.