@inproceedings{xu-etal-2024-symbol,
title = "Symbol-{LLM}: Towards Foundational Symbol-centric Interface For Large Language Models",
author = "Xu, Fangzhi and
Wu, Zhiyong and
Sun, Qiushi and
Ren, Siyu and
Yuan, Fei and
Yuan, Shuai and
Lin, Qika and
Qiao, Yu and
Liu, Jun",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.707",
pages = "13091--13116",
abstract = "Although Large Language Models (LLMs) demonstrate remarkable ability in processing and generating human-like text, they do have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language(e.g., chemical molecular formula). Injecting a collection of symbolic data directly into the training of LLMs can be problematic, as it disregards the synergies among different symbolic families and overlooks the need for a balanced mixture of natural and symbolic data. In this work, we tackle these challenges from both a data and framework perspective and introduce Symbol-LLM series models. First, we curated a data collection consisting of 34 tasks and incorporating 20 distinct symbolic families, intending to capture the interrelations and foster synergies between symbols. Then, a two-stage tuning framework succeeds in injecting symbolic knowledge without loss of the generality ability. Extensive experiments on both symbol- and NL-centric tasks demonstrate the balanced and superior performances of Symbol-LLM series models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2024-symbol">
<titleInfo>
<title>Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fangzhi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyong</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiushi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyu</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qika</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Qiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although Large Language Models (LLMs) demonstrate remarkable ability in processing and generating human-like text, they do have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language(e.g., chemical molecular formula). Injecting a collection of symbolic data directly into the training of LLMs can be problematic, as it disregards the synergies among different symbolic families and overlooks the need for a balanced mixture of natural and symbolic data. In this work, we tackle these challenges from both a data and framework perspective and introduce Symbol-LLM series models. First, we curated a data collection consisting of 34 tasks and incorporating 20 distinct symbolic families, intending to capture the interrelations and foster synergies between symbols. Then, a two-stage tuning framework succeeds in injecting symbolic knowledge without loss of the generality ability. Extensive experiments on both symbol- and NL-centric tasks demonstrate the balanced and superior performances of Symbol-LLM series models.</abstract>
<identifier type="citekey">xu-etal-2024-symbol</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.707</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13091</start>
<end>13116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models
%A Xu, Fangzhi
%A Wu, Zhiyong
%A Sun, Qiushi
%A Ren, Siyu
%A Yuan, Fei
%A Yuan, Shuai
%A Lin, Qika
%A Qiao, Yu
%A Liu, Jun
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F xu-etal-2024-symbol
%X Although Large Language Models (LLMs) demonstrate remarkable ability in processing and generating human-like text, they do have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language(e.g., chemical molecular formula). Injecting a collection of symbolic data directly into the training of LLMs can be problematic, as it disregards the synergies among different symbolic families and overlooks the need for a balanced mixture of natural and symbolic data. In this work, we tackle these challenges from both a data and framework perspective and introduce Symbol-LLM series models. First, we curated a data collection consisting of 34 tasks and incorporating 20 distinct symbolic families, intending to capture the interrelations and foster synergies between symbols. Then, a two-stage tuning framework succeeds in injecting symbolic knowledge without loss of the generality ability. Extensive experiments on both symbol- and NL-centric tasks demonstrate the balanced and superior performances of Symbol-LLM series models.
%U https://aclanthology.org/2024.acl-long.707
%P 13091-13116
Markdown (Informal)
[Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models](https://aclanthology.org/2024.acl-long.707) (Xu et al., ACL 2024)
ACL
- Fangzhi Xu, Zhiyong Wu, Qiushi Sun, Siyu Ren, Fei Yuan, Shuai Yuan, Qika Lin, Yu Qiao, and Jun Liu. 2024. Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13091–13116, Bangkok, Thailand. Association for Computational Linguistics.