Experiments with LLMs for Converting Language to Logic
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A9ML98IU4" target="_blank" >RIV/00216208:11320/25:9ML98IU4 - isvavai.cz</a>
Result on the web
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204913636&doi=10.1007%2f978-3-031-71170-1_24&partnerID=40&md5=3231ee8dbc08e350ce25149222f50340" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204913636&doi=10.1007%2f978-3-031-71170-1_24&partnerID=40&md5=3231ee8dbc08e350ce25149222f50340</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-71170-1_24" target="_blank" >10.1007/978-3-031-71170-1_24</a>
Alternative languages
Result language
angličtina
Original language name
Experiments with LLMs for Converting Language to Logic
Original language description
While the meaning of “semantic parsing” covers a wide spectrum, we consider converting English to first order predicate logic (FOL) with the help of large language models (LLMs). The paper focuses on experiments with different approaches of using an LLM for semantic parsing to FOL: from standalone zero-shot and multishot scenarios to the use as a specialized component in several stages of the semantic parser pipeline. The goal of the experiments is to determine promising approaches for including LLM components into a question answering pipeline built around a logical reasoner with extensions for commonsense reasoning. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Lect. Notes Comput. Sci.
ISBN
978-303171169-5
ISSN
0302-9743
e-ISSN
—
Number of pages
10
Pages from-to
305-314
Publisher name
Springer Science and Business Media Deutschland GmbH
Place of publication
—
Event location
Barcelona
Event date
Jan 1, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—