@inproceedings{xu-wang-2025-investigating,
title = "Investigating the (De)Composition Capabilities of Large Language Models in Natural-to-Formal Language Conversion",
author = "Xu, Ziyao and
Wang, Houfeng",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.87/",
doi = "10.18653/v1/2025.naacl-long.87",
pages = "1767--1783",
ISBN = "979-8-89176-189-6",
abstract = "Humans have strong capabilities of decomposition and composition in natural-to-formal language conversion (N2F) when faced with an unfamiliar formal language, and can easily cope with compositional gaps and counter-intuitive symbolic names. To investigate whether large language models (LLMs) have this set of basic capabilities in N2F, we propose the STD framework. This framework semi-automatically performs sample and task construction, allowing decoupled evaluation of the set of decomposition and composition capabilities of LLMs in N2F. Based on this framework, we evaluate and analyze the most advanced LLMs, and the main findings include that: (1) the LLMs are deficient in both decomposition and composition; (2) the LLMs show a wide coverage of error types that can be attributed to deficiencies in natural language understanding and the learning and use of symbolic systems; (3) compositional gaps and counter-intuitive symbolic names both affect the decomposition and composition of the LLMs. Our work provides a new perspective for investigating the basic capabilities of decomposition and composition of LLMs in N2F. The detailed analysis of deficiencies and attributions can help subsequent improvements of LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-wang-2025-investigating">
<titleInfo>
<title>Investigating the (De)Composition Capabilities of Large Language Models in Natural-to-Formal Language Conversion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziyao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houfeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Humans have strong capabilities of decomposition and composition in natural-to-formal language conversion (N2F) when faced with an unfamiliar formal language, and can easily cope with compositional gaps and counter-intuitive symbolic names. To investigate whether large language models (LLMs) have this set of basic capabilities in N2F, we propose the STD framework. This framework semi-automatically performs sample and task construction, allowing decoupled evaluation of the set of decomposition and composition capabilities of LLMs in N2F. Based on this framework, we evaluate and analyze the most advanced LLMs, and the main findings include that: (1) the LLMs are deficient in both decomposition and composition; (2) the LLMs show a wide coverage of error types that can be attributed to deficiencies in natural language understanding and the learning and use of symbolic systems; (3) compositional gaps and counter-intuitive symbolic names both affect the decomposition and composition of the LLMs. Our work provides a new perspective for investigating the basic capabilities of decomposition and composition of LLMs in N2F. The detailed analysis of deficiencies and attributions can help subsequent improvements of LLMs.</abstract>
<identifier type="citekey">xu-wang-2025-investigating</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.87</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.87/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>1767</start>
<end>1783</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating the (De)Composition Capabilities of Large Language Models in Natural-to-Formal Language Conversion
%A Xu, Ziyao
%A Wang, Houfeng
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F xu-wang-2025-investigating
%X Humans have strong capabilities of decomposition and composition in natural-to-formal language conversion (N2F) when faced with an unfamiliar formal language, and can easily cope with compositional gaps and counter-intuitive symbolic names. To investigate whether large language models (LLMs) have this set of basic capabilities in N2F, we propose the STD framework. This framework semi-automatically performs sample and task construction, allowing decoupled evaluation of the set of decomposition and composition capabilities of LLMs in N2F. Based on this framework, we evaluate and analyze the most advanced LLMs, and the main findings include that: (1) the LLMs are deficient in both decomposition and composition; (2) the LLMs show a wide coverage of error types that can be attributed to deficiencies in natural language understanding and the learning and use of symbolic systems; (3) compositional gaps and counter-intuitive symbolic names both affect the decomposition and composition of the LLMs. Our work provides a new perspective for investigating the basic capabilities of decomposition and composition of LLMs in N2F. The detailed analysis of deficiencies and attributions can help subsequent improvements of LLMs.
%R 10.18653/v1/2025.naacl-long.87
%U https://aclanthology.org/2025.naacl-long.87/
%U https://doi.org/10.18653/v1/2025.naacl-long.87
%P 1767-1783
Markdown (Informal)
[Investigating the (De)Composition Capabilities of Large Language Models in Natural-to-Formal Language Conversion](https://aclanthology.org/2025.naacl-long.87/) (Xu & Wang, NAACL 2025)
ACL