@inproceedings{wang-etal-2025-leveraging,
title = "Leveraging Language-based Representations for Better Solving Symbol-related Problems with Large Language Models",
author = "Wang, Yile and
Cheng, Sijie and
Sun, Zixin and
Li, Peng and
Liu, Yang",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.372/",
pages = "5544--5557",
abstract = "Symbols such as numerical sequences, chemical formulas, and table delimiters exist widely, playing important roles in symbol-related tasks such as abstract reasoning, chemical property prediction, and tabular question-answering. Compared to tasks based on natural language expressions, large language models (LLMs) have limitations in understanding and reasoning on symbol-based representations, making it difficult for them to handle symbol-related problems. In this paper, we propose symbol-to-language (S2L), a method that converts symbol-based representations to language-based representations, providing valuable information for language models during reasoning. We found that, for both closed-source and open-source LLMs, the capability to solve symbol-related problems can be largely enhanced by incorporating such language-based representations. For example, by employing S2L for GPT-4, there can be substantial improvements of +21.9{\%} and +9.5{\%} accuracy for 1D-ARC and Dyck language tasks, respectively. There is also a consistent improvement in other six general symbol-related tasks such as table understanding and Tweet analysis. We release the GPT logs in https://github.com/THUNLP-MT/symbol2language."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-leveraging">
<titleInfo>
<title>Leveraging Language-based Representations for Better Solving Symbol-related Problems with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yile</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sijie</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixin</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Symbols such as numerical sequences, chemical formulas, and table delimiters exist widely, playing important roles in symbol-related tasks such as abstract reasoning, chemical property prediction, and tabular question-answering. Compared to tasks based on natural language expressions, large language models (LLMs) have limitations in understanding and reasoning on symbol-based representations, making it difficult for them to handle symbol-related problems. In this paper, we propose symbol-to-language (S2L), a method that converts symbol-based representations to language-based representations, providing valuable information for language models during reasoning. We found that, for both closed-source and open-source LLMs, the capability to solve symbol-related problems can be largely enhanced by incorporating such language-based representations. For example, by employing S2L for GPT-4, there can be substantial improvements of +21.9% and +9.5% accuracy for 1D-ARC and Dyck language tasks, respectively. There is also a consistent improvement in other six general symbol-related tasks such as table understanding and Tweet analysis. We release the GPT logs in https://github.com/THUNLP-MT/symbol2language.</abstract>
<identifier type="citekey">wang-etal-2025-leveraging</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.372/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>5544</start>
<end>5557</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Language-based Representations for Better Solving Symbol-related Problems with Large Language Models
%A Wang, Yile
%A Cheng, Sijie
%A Sun, Zixin
%A Li, Peng
%A Liu, Yang
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F wang-etal-2025-leveraging
%X Symbols such as numerical sequences, chemical formulas, and table delimiters exist widely, playing important roles in symbol-related tasks such as abstract reasoning, chemical property prediction, and tabular question-answering. Compared to tasks based on natural language expressions, large language models (LLMs) have limitations in understanding and reasoning on symbol-based representations, making it difficult for them to handle symbol-related problems. In this paper, we propose symbol-to-language (S2L), a method that converts symbol-based representations to language-based representations, providing valuable information for language models during reasoning. We found that, for both closed-source and open-source LLMs, the capability to solve symbol-related problems can be largely enhanced by incorporating such language-based representations. For example, by employing S2L for GPT-4, there can be substantial improvements of +21.9% and +9.5% accuracy for 1D-ARC and Dyck language tasks, respectively. There is also a consistent improvement in other six general symbol-related tasks such as table understanding and Tweet analysis. We release the GPT logs in https://github.com/THUNLP-MT/symbol2language.
%U https://aclanthology.org/2025.coling-main.372/
%P 5544-5557
Markdown (Informal)
[Leveraging Language-based Representations for Better Solving Symbol-related Problems with Large Language Models](https://aclanthology.org/2025.coling-main.372/) (Wang et al., COLING 2025)
ACL