When Do Program-of-Thoughts Work for Reasoning?
In the realm of embodied artificial intelligence, the reasoning capabilities of Large Language Models (LLMs) play a pivotal role. Although there are effective methods like program-of-thought prompting for LLMs which uses programming language to tackle complex reasoning tasks, the specific impact of...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
18.12.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | In the realm of embodied artificial intelligence, the reasoning capabilities of Large Language Models (LLMs) play a pivotal role. Although there are effective methods like program-of-thought prompting for LLMs which uses programming language to tackle complex reasoning tasks, the specific impact of code data on the improvement of reasoning capabilities remains under-explored. To address this gap, we propose complexity-impacted reasoning score (CIRS), which combines structural and logical attributes, to measure the correlation between code and reasoning abilities. Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity by considering the difficulty and the cyclomatic complexity. Through an empirical analysis, we find not all code data of complexity can be learned or understood by LLMs. Optimal level of complexity is critical to the improvement of reasoning abilities by program-aided prompting. Then we design an auto-synthesizing and stratifying algorithm, and apply it to instruction generation for mathematical reasoning and code data filtering for code generation tasks. Extensive results demonstrates the effectiveness of our proposed approach. Code will be integrated into the EasyInstruct framework at https://github.com/zjunlp/EasyInstruct. |
---|---|
AbstractList | In the realm of embodied artificial intelligence, the reasoning capabilities of Large Language Models (LLMs) play a pivotal role. Although there are effective methods like program-of-thought prompting for LLMs which uses programming language to tackle complex reasoning tasks, the specific impact of code data on the improvement of reasoning capabilities remains under-explored. To address this gap, we propose complexity-impacted reasoning score (CIRS), which combines structural and logical attributes, to measure the correlation between code and reasoning abilities. Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity by considering the difficulty and the cyclomatic complexity. Through an empirical analysis, we find not all code data of complexity can be learned or understood by LLMs. Optimal level of complexity is critical to the improvement of reasoning abilities by program-aided prompting. Then we design an auto-synthesizing and stratifying algorithm, and apply it to instruction generation for mathematical reasoning and code data filtering for code generation tasks. Extensive results demonstrates the effectiveness of our proposed approach. Code will be integrated into the EasyInstruct framework at https://github.com/zjunlp/EasyInstruct. |
Author | Jiang, Yinuo Zhang, Ningyu Zheng, Guozhou Bi, Zhen Deng, Shumin Chen, Huajun |
Author_xml | – sequence: 1 givenname: Zhen surname: Bi fullname: Bi, Zhen – sequence: 2 givenname: Ningyu surname: Zhang fullname: Zhang, Ningyu – sequence: 3 givenname: Yinuo surname: Jiang fullname: Jiang, Yinuo – sequence: 4 givenname: Shumin surname: Deng fullname: Deng, Shumin – sequence: 5 givenname: Guozhou surname: Zheng fullname: Zheng, Guozhou – sequence: 6 givenname: Huajun surname: Chen fullname: Chen, Huajun |
BookMark | eNqNyrsKwjAUgOGDKFi17xBwDsYTY7M5eMFRpNCxZMjFqjmatO-vgw_g9A_fP4NxpGhHUKCUa643iFMoc-6EELitUClZwKoJNrIDsUsin8yTk-N1oMGHPrOG0p05SuxqTaZ4i363gIkzj2zLX-ewPB3r_Zm_Er0Hm_u2oyHFL7WoldaiQi3lf9cHEKwz6Q |
ContentType | Paper |
Copyright | 2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_28588072833 |
IEDL.DBID | BENPR |
IngestDate | Thu Oct 10 17:58:41 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_28588072833 |
OpenAccessLink | https://www.proquest.com/docview/2858807283?pq-origsite=%requestingapplication% |
PQID | 2858807283 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2858807283 |
PublicationCentury | 2000 |
PublicationDate | 20231218 |
PublicationDateYYYYMMDD | 2023-12-18 |
PublicationDate_xml | – month: 12 year: 2023 text: 20231218 day: 18 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2023 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.5166414 |
SecondaryResourceType | preprint |
Snippet | In the realm of embodied artificial intelligence, the reasoning capabilities of Large Language Models (LLMs) play a pivotal role. Although there are effective... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Algorithms Artificial intelligence Empirical analysis Large language models Programming languages Reasoning Task complexity |
Title | When Do Program-of-Thoughts Work for Reasoning? |
URI | https://www.proquest.com/docview/2858807283 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1NSwMxEB1sF8Fb_cKPWgJ6DW2ym2xyKqi7FqFlKRV6K2s2wVO3NuvV326SbvUg9BgCSQjDm5k3wzyABzMqY2ZcmkpUKnHCjcKCsRhTXhFT-RFwQT9lOuOTt-R1yZYt4Wbbtso9JgagrmrlOfIhFcyZWuq84Xjzib1qlK-uthIaHYgoSXyZNnrMZsX8l2WhPHUxc_wPaIP3yHsQFeVGb0_hSK_P4Dg0XSp7DkOHhGv0XKNi1ySFa4MXH142p7HIs9jIRZRorksbONPxBdzn2eJpgve3rFpLsKu_d8eX0HUpvb4CxEelcq5VSC5kQv1EJyNNRViqqRCS6WvoHzrp5vD2LZx4UXTfdEFEH7rN9kvfOdfZvA-gI_KXQftLbjX9zn4A6Np2rA |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1dS8MwFL1oi7g3P_FjakBfw9aPpMnTQN2oupUyKuyt1DbBp3Wu9f8vN3b6IOw5kIRwuefek8M9AA96WARMmzbVKyNJQ65LKhgLqM8rT1c4As76p8wSHr-Hrwu26Ai3ppNVbnOiTdRVXSJHPvAFM6EWGTQcrb4oukbh72pnobEPLo7cFA64j-Mknf-yLD6PTM0c_Eu0Fj0mR-CmxUqtj2FPLU_gwIouy-YUBiYTLslzTdIfkRStNc0-0TanbQiy2MRUlGSuisZypqMzuJ-Ms6eYbk_Ju0ho8r97B-fgmJZeXQDhw6I00CokFzL0caKTlrryWKR8ISRTl9DftdPV7uU7OIyz2TSfviRv19BDg3QUYHiiD067_lY3Bkbbj9vurTYOiHeL |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=When+Do+Program-of-Thoughts+Work+for+Reasoning%3F&rft.jtitle=arXiv.org&rft.au=Bi%2C+Zhen&rft.au=Zhang%2C+Ningyu&rft.au=Jiang%2C+Yinuo&rft.au=Deng%2C+Shumin&rft.date=2023-12-18&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |