@inproceedings{atwell-etal-2026-asking,
title = "Asking the Right Questions: Can expert-prompted {LLM}s reformulate legal queries from non-experts?",
author = "Atwell, Katherine and
Gray, Morgan A. and
Savelka, Jaromir and
Rial, Len and
Linardi, Sera and
Alikhani, Malihe",
editor = "Mysore, Sheshera and
Kumar, Sachin and
Balachandran, Vidhisha and
Hayati, Shirley Anugrah and
Brahman, Faeze and
Moussa, Hanane Nour and
Salemi, Alireza",
booktitle = "Proceedings of the Second Workshop on Customizable {NLP}: Progress and Challenges in Customizing {NLP} for a Domain, Application, Group, or Individual ({C}ustom{NLP}4{U})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.customnlp4u-1.15/",
pages = "167--181",
ISBN = "979-8-89176-396-8",
abstract = "Large language models are widely used by everyday users, and can be asked to perform tasks that require specialized expertise, such as interpreting contractual terms and conditions, filing personal taxes, or diagnosing medical symptoms. Although these tools should not be used in place of professional advice, they can be useful starting points for users seeking professional help, improving users' access and interactions with professionals. In this vein, this paper introduces a legal question reformulation task to assist non-experts in their interactions with lawyers. This has the potential to streamline discussions between lawyers and clients, who may not know the correct legal language to communicate their needs. Using a novel evaluation framework informed by legal expertise, we investigate the quality of model-generated legal question reformulations on in-the-wild data from non-experts seeking legal advice. Our findings indicate that LLMs have significant potential in legal reasoning, but some unexpected safety concerns may emerge. Further, adding linguisticallyaligned in-domain text samples can improve performance for smaller models, even when the samples are not aligned factually with the given question."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="atwell-etal-2026-asking">
<titleInfo>
<title>Asking the Right Questions: Can expert-prompted LLMs reformulate legal queries from non-experts?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Atwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Morgan</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Gray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaromir</namePart>
<namePart type="family">Savelka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Len</namePart>
<namePart type="family">Rial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sera</namePart>
<namePart type="family">Linardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheshera</namePart>
<namePart type="family">Mysore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vidhisha</namePart>
<namePart type="family">Balachandran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shirley</namePart>
<namePart type="given">Anugrah</namePart>
<namePart type="family">Hayati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faeze</namePart>
<namePart type="family">Brahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanane</namePart>
<namePart type="given">Nour</namePart>
<namePart type="family">Moussa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alireza</namePart>
<namePart type="family">Salemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-396-8</identifier>
</relatedItem>
<abstract>Large language models are widely used by everyday users, and can be asked to perform tasks that require specialized expertise, such as interpreting contractual terms and conditions, filing personal taxes, or diagnosing medical symptoms. Although these tools should not be used in place of professional advice, they can be useful starting points for users seeking professional help, improving users’ access and interactions with professionals. In this vein, this paper introduces a legal question reformulation task to assist non-experts in their interactions with lawyers. This has the potential to streamline discussions between lawyers and clients, who may not know the correct legal language to communicate their needs. Using a novel evaluation framework informed by legal expertise, we investigate the quality of model-generated legal question reformulations on in-the-wild data from non-experts seeking legal advice. Our findings indicate that LLMs have significant potential in legal reasoning, but some unexpected safety concerns may emerge. Further, adding linguisticallyaligned in-domain text samples can improve performance for smaller models, even when the samples are not aligned factually with the given question.</abstract>
<identifier type="citekey">atwell-etal-2026-asking</identifier>
<location>
<url>https://aclanthology.org/2026.customnlp4u-1.15/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>167</start>
<end>181</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Asking the Right Questions: Can expert-prompted LLMs reformulate legal queries from non-experts?
%A Atwell, Katherine
%A Gray, Morgan A.
%A Savelka, Jaromir
%A Rial, Len
%A Linardi, Sera
%A Alikhani, Malihe
%Y Mysore, Sheshera
%Y Kumar, Sachin
%Y Balachandran, Vidhisha
%Y Hayati, Shirley Anugrah
%Y Brahman, Faeze
%Y Moussa, Hanane Nour
%Y Salemi, Alireza
%S Proceedings of the Second Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-396-8
%F atwell-etal-2026-asking
%X Large language models are widely used by everyday users, and can be asked to perform tasks that require specialized expertise, such as interpreting contractual terms and conditions, filing personal taxes, or diagnosing medical symptoms. Although these tools should not be used in place of professional advice, they can be useful starting points for users seeking professional help, improving users’ access and interactions with professionals. In this vein, this paper introduces a legal question reformulation task to assist non-experts in their interactions with lawyers. This has the potential to streamline discussions between lawyers and clients, who may not know the correct legal language to communicate their needs. Using a novel evaluation framework informed by legal expertise, we investigate the quality of model-generated legal question reformulations on in-the-wild data from non-experts seeking legal advice. Our findings indicate that LLMs have significant potential in legal reasoning, but some unexpected safety concerns may emerge. Further, adding linguisticallyaligned in-domain text samples can improve performance for smaller models, even when the samples are not aligned factually with the given question.
%U https://aclanthology.org/2026.customnlp4u-1.15/
%P 167-181
Markdown (Informal)
[Asking the Right Questions: Can expert-prompted LLMs reformulate legal queries from non-experts?](https://aclanthology.org/2026.customnlp4u-1.15/) (Atwell et al., CustomNLP4U 2026)
ACL
- Katherine Atwell, Morgan A. Gray, Jaromir Savelka, Len Rial, Sera Linardi, and Malihe Alikhani. 2026. Asking the Right Questions: Can expert-prompted LLMs reformulate legal queries from non-experts?. In Proceedings of the Second Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U), pages 167–181, San Diego, California, USA. Association for Computational Linguistics.