Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator

Hyunji Lee; Kevin Chenhao Li; Matthias Grabmair; Shanshan Xu

Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator

Hyunji Lee, Kevin Chenhao Li, Matthias Grabmair, Shanshan Xu

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

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.

Anthology ID:: 2025.nllp-1.18
Volume:: Proceedings of the Natural Legal Language Processing Workshop 2025
Month:: November
Year:: 2025
Address:: Suzhou, China
Editors:: Nikolaos Aletras, Ilias Chalkidis, Leslie Barrett, Cătălina Goanță, Daniel Preoțiuc-Pietro, Gerasimos Spanakis
Venues:: NLLP | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 281–290
Language:
URL:: https://aclanthology.org/2025.nllp-1.18/
DOI:
Bibkey:
Cite (ACL):: Hyunji Lee, Kevin Chenhao Li, Matthias Grabmair, and Shanshan Xu. 2025. Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator. In Proceedings of the Natural Legal Language Processing Workshop 2025, pages 281–290, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):: Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator (Lee et al., NLLP 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.nllp-1.18.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{lee-etal-2025-efficient,
    title = "Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator",
    author = "Lee, Hyunji  and
      Li, Kevin Chenhao  and
      Grabmair, Matthias  and
      Xu, Shanshan",
    editor = "Aletras, Nikolaos  and
      Chalkidis, Ilias  and
      Barrett, Leslie  and
      Goanț{\u{a}}, C{\u{a}}t{\u{a}}lina  and
      Preoțiuc-Pietro, Daniel  and
      Spanakis, Gerasimos",
    booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.nllp-1.18/",
    pages = "281--290",
    ISBN = "979-8-89176-338-8",
    abstract = "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."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2025-efficient">
    <titleInfo>
        <title>Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hyunji</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="given">Chenhao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthias</namePart>
        <namePart type="family">Grabmair</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shanshan</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Natural Legal Language Processing Workshop 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Nikolaos</namePart>
            <namePart type="family">Aletras</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ilias</namePart>
            <namePart type="family">Chalkidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leslie</namePart>
            <namePart type="family">Barrett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Cătălina</namePart>
            <namePart type="family">Goanță</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daniel</namePart>
            <namePart type="family">Preoțiuc-Pietro</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gerasimos</namePart>
            <namePart type="family">Spanakis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-338-8</identifier>
    </relatedItem>
    <abstract>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.</abstract>
    <identifier type="citekey">lee-etal-2025-efficient</identifier>
    <location>
        <url>https://aclanthology.org/2025.nllp-1.18/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>281</start>
            <end>290</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator
%A Lee, Hyunji
%A Li, Kevin Chenhao
%A Grabmair, Matthias
%A Xu, Shanshan
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goanță, Cătălina
%Y Preoțiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%S Proceedings of the Natural Legal Language Processing Workshop 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-338-8
%F lee-etal-2025-efficient
%X 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.
%U https://aclanthology.org/2025.nllp-1.18/
%P 281-290

Download as File

Markdown (Informal)

[Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator](https://aclanthology.org/2025.nllp-1.18/) (Lee et al., NLLP 2025)

Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator (Lee et al., NLLP 2025)

ACL

Hyunji Lee, Kevin Chenhao Li, Matthias Grabmair, and Shanshan Xu. 2025. Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator. In Proceedings of the Natural Legal Language Processing Workshop 2025, pages 281–290, Suzhou, China. Association for Computational Linguistics.