@inproceedings{chen-etal-2026-code,
title = "Code-Prompt: Evaluating Code-{LLM}s for Natural Language Tasks via Code Aligned Prompts",
author = {Chen, Yuxuan and
Thomas, Philippe and
Oehring, Robert and
Krenzien, Felix and
M{\"o}ller, Sebastian and
Roller, Roland},
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.31/",
pages = "580--604",
ISBN = "979-8-89176-444-6",
abstract = "Large language models pre-trained on code (Code-LLMs) have achieved remarkable performance on coding tasks. Despite their success of processing programming language, their application to natural language tasks has largely been limited to narrow tasks and ad-hoc model selection. In this paper, we present Code-Prompt, a comprehensive prompt-based framework to benchmark Code-LLMs over ten NLP tasks. We evaluate Code-Prompt on 13 Code-LLMs using code-aligned prompts and compare them with their parallel natural language LLMs (NL-LLMs) using natural language prompts.\par Our results show that Code-LLMs perform on par with NL-LLMs across a range of NLP tasks, while producing more format-consistent generation with less redundancy. Our cross-lingual experiments further indicate that knowledge in Code-LLMs is well shared among different programming languages, whereas performance across different human languages still varies significantly. All our code and data will be made publicly available at https://github.com/chen-yuxuan/code-prompt."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-code">
<titleInfo>
<title>Code-Prompt: Evaluating Code-LLMs for Natural Language Tasks via Code Aligned Prompts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Oehring</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Krenzien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Möller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roland</namePart>
<namePart type="family">Roller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Large language models pre-trained on code (Code-LLMs) have achieved remarkable performance on coding tasks. Despite their success of processing programming language, their application to natural language tasks has largely been limited to narrow tasks and ad-hoc model selection. In this paper, we present Code-Prompt, a comprehensive prompt-based framework to benchmark Code-LLMs over ten NLP tasks. We evaluate Code-Prompt on 13 Code-LLMs using code-aligned prompts and compare them with their parallel natural language LLMs (NL-LLMs) using natural language prompts.\par Our results show that Code-LLMs perform on par with NL-LLMs across a range of NLP tasks, while producing more format-consistent generation with less redundancy. Our cross-lingual experiments further indicate that knowledge in Code-LLMs is well shared among different programming languages, whereas performance across different human languages still varies significantly. All our code and data will be made publicly available at https://github.com/chen-yuxuan/code-prompt.</abstract>
<identifier type="citekey">chen-etal-2026-code</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.31/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>580</start>
<end>604</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Code-Prompt: Evaluating Code-LLMs for Natural Language Tasks via Code Aligned Prompts
%A Chen, Yuxuan
%A Thomas, Philippe
%A Oehring, Robert
%A Krenzien, Felix
%A Möller, Sebastian
%A Roller, Roland
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F chen-etal-2026-code
%X Large language models pre-trained on code (Code-LLMs) have achieved remarkable performance on coding tasks. Despite their success of processing programming language, their application to natural language tasks has largely been limited to narrow tasks and ad-hoc model selection. In this paper, we present Code-Prompt, a comprehensive prompt-based framework to benchmark Code-LLMs over ten NLP tasks. We evaluate Code-Prompt on 13 Code-LLMs using code-aligned prompts and compare them with their parallel natural language LLMs (NL-LLMs) using natural language prompts.\par Our results show that Code-LLMs perform on par with NL-LLMs across a range of NLP tasks, while producing more format-consistent generation with less redundancy. Our cross-lingual experiments further indicate that knowledge in Code-LLMs is well shared among different programming languages, whereas performance across different human languages still varies significantly. All our code and data will be made publicly available at https://github.com/chen-yuxuan/code-prompt.
%U https://aclanthology.org/2026.findings-aacl.31/
%P 580-604
Markdown (Informal)
[Code-Prompt: Evaluating Code-LLMs for Natural Language Tasks via Code Aligned Prompts](https://aclanthology.org/2026.findings-aacl.31/) (Chen et al., Findings 2026)
ACL