In-Context Symbolic Regression : Leveraging Large Language Models for Function Discovery

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

Abstrakti

State of the art Symbolic Regression (SR) methods currently build specialized models, while the application of Large Language Models (LLMs) remains largely unexplored. In this work, we introduce the first comprehensive framework that utilizes LLMs for the task of SR. We propose In-Context Symbolic Regression (ICSR), an SR method which iteratively refines a functional form with an LLM and determines its coefficients with an external optimizer. ICSR leverages LLMs’ strong mathematical prior both to propose an initial set of possible functions given the observations and to refine them based on their errors. Our findings reveal that LLMs are able to successfully find symbolic equations that fit the given data, matching or outperforming the overall performance of the best SR baselines on four popular benchmarks, while yielding simpler equations with better out of distribution generalization.

AlkuperäiskieliEnglanti
OtsikkoProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
ToimittajatXiyan Fu, Eve Fleisig
KustantajaAssociation for Computational Linguistics
Sivut589-606
Sivumäärä18
ISBN (elektroninen)9798891760974
TilaJulkaistu - 2024
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaAnnual Meeting of the Association for Computational Linguistics - Bangkok, Thaimaa
Kesto: 11 elok. 202416 elok. 2024
Konferenssinumero: 62

Julkaisusarja

NimiProceedings of the Annual Meeting of the Association for Computational Linguistics
KustantajaAssociation for Computational Linguistics
Vuosikerta4
ISSN (painettu)0736-587X

Conference

ConferenceAnnual Meeting of the Association for Computational Linguistics
LyhennettäACL
Maa/AlueThaimaa
KaupunkiBangkok
Ajanjakso11/08/202416/08/2024

Sormenjälki

Sukella tutkimusaiheisiin 'In-Context Symbolic Regression : Leveraging Large Language Models for Function Discovery'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä