@inproceedings{ali-etal-2026-evidence,
title = "Evidence-Grounded Contract Clause Classification with Small Language Models",
author = "Ali, Dina Mohamed and
Allam, Hager Hamed Abd Elrady and
Rezk, Hayam Abdelbaset and
Ferdousi, Rahatara and
AbdElhamed, Mohammed Anber",
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 and
Xu, Shanshan",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nllp-1.7/",
pages = "55--63",
ISBN = "979-8-89176-494-1",
abstract = "Commercial contract clauses exhibit substantial linguistic variation and semantic overlap, making fine-grained classification challenging for small language models (SLMs). We investigate whether retrieving semantically similar labeled clauses can provide task-specific evidence at inference time and improve classification without modifying the underlying SLM. Using the Contract Understanding Atticus Dataset (CUAD), we formulate clause classification as a retrieval-conditioned prediction task in which relevant training clauses are retrieved and provided as in-context demonstrations to a locally deployed SLM. We evaluate prompting-only, retrieval-only, and retrieval-conditioned configurations on the same contract-disjoint held-out set of 1,679 clauses. The proposed retrieval-conditioned SLM achieves 66.41{\%} accuracy and 51.72{\%} macro-F1, compared with 35.80{\%} and 31.41{\%} for the zero-shot SLM and 50.98{\%} and 40.93{\%} for the random few-shot SLM, respectively. Retrieval-only nearest-neighbor baselines achieve 47.48{--}47.82{\%} macro-F1, while conditioning the SLM on the same retrieved evidence increases macro-F1 to 51.72{\%}. These results show that retrieval provides substantial task-specific context and that SLM conditioning provides additional improvement beyond direct nearest-neighbor label assignment, without task-specific parameter fine-tuning. The findings support retrieval-conditioned SLMs as a promising direction for evidence-grounded and locally deployable legal NLP"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ali-etal-2026-evidence">
<titleInfo>
<title>Evidence-Grounded Contract Clause Classification with Small Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hager</namePart>
<namePart type="given">Hamed</namePart>
<namePart type="given">Abd</namePart>
<namePart type="given">Elrady</namePart>
<namePart type="family">Allam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hayam</namePart>
<namePart type="given">Abdelbaset</namePart>
<namePart type="family">Rezk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahatara</namePart>
<namePart type="family">Ferdousi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Anber</namePart>
<namePart type="family">AbdElhamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2026</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>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-494-1</identifier>
</relatedItem>
<abstract>Commercial contract clauses exhibit substantial linguistic variation and semantic overlap, making fine-grained classification challenging for small language models (SLMs). We investigate whether retrieving semantically similar labeled clauses can provide task-specific evidence at inference time and improve classification without modifying the underlying SLM. Using the Contract Understanding Atticus Dataset (CUAD), we formulate clause classification as a retrieval-conditioned prediction task in which relevant training clauses are retrieved and provided as in-context demonstrations to a locally deployed SLM. We evaluate prompting-only, retrieval-only, and retrieval-conditioned configurations on the same contract-disjoint held-out set of 1,679 clauses. The proposed retrieval-conditioned SLM achieves 66.41% accuracy and 51.72% macro-F1, compared with 35.80% and 31.41% for the zero-shot SLM and 50.98% and 40.93% for the random few-shot SLM, respectively. Retrieval-only nearest-neighbor baselines achieve 47.48–47.82% macro-F1, while conditioning the SLM on the same retrieved evidence increases macro-F1 to 51.72%. These results show that retrieval provides substantial task-specific context and that SLM conditioning provides additional improvement beyond direct nearest-neighbor label assignment, without task-specific parameter fine-tuning. The findings support retrieval-conditioned SLMs as a promising direction for evidence-grounded and locally deployable legal NLP</abstract>
<identifier type="citekey">ali-etal-2026-evidence</identifier>
<location>
<url>https://aclanthology.org/2026.nllp-1.7/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>55</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evidence-Grounded Contract Clause Classification with Small Language Models
%A Ali, Dina Mohamed
%A Allam, Hager Hamed Abd Elrady
%A Rezk, Hayam Abdelbaset
%A Ferdousi, Rahatara
%A AbdElhamed, Mohammed Anber
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goanță, Cătălina
%Y Preoțiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%Y Xu, Shanshan
%S Proceedings of the Natural Legal Language Processing Workshop 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-494-1
%F ali-etal-2026-evidence
%X Commercial contract clauses exhibit substantial linguistic variation and semantic overlap, making fine-grained classification challenging for small language models (SLMs). We investigate whether retrieving semantically similar labeled clauses can provide task-specific evidence at inference time and improve classification without modifying the underlying SLM. Using the Contract Understanding Atticus Dataset (CUAD), we formulate clause classification as a retrieval-conditioned prediction task in which relevant training clauses are retrieved and provided as in-context demonstrations to a locally deployed SLM. We evaluate prompting-only, retrieval-only, and retrieval-conditioned configurations on the same contract-disjoint held-out set of 1,679 clauses. The proposed retrieval-conditioned SLM achieves 66.41% accuracy and 51.72% macro-F1, compared with 35.80% and 31.41% for the zero-shot SLM and 50.98% and 40.93% for the random few-shot SLM, respectively. Retrieval-only nearest-neighbor baselines achieve 47.48–47.82% macro-F1, while conditioning the SLM on the same retrieved evidence increases macro-F1 to 51.72%. These results show that retrieval provides substantial task-specific context and that SLM conditioning provides additional improvement beyond direct nearest-neighbor label assignment, without task-specific parameter fine-tuning. The findings support retrieval-conditioned SLMs as a promising direction for evidence-grounded and locally deployable legal NLP
%U https://aclanthology.org/2026.nllp-1.7/
%P 55-63
Markdown (Informal)
[Evidence-Grounded Contract Clause Classification with Small Language Models](https://aclanthology.org/2026.nllp-1.7/) (Ali et al., NLLP 2026)
ACL