Exploring Abductive Reasoning in Language Models for Data-to-Text Generation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10492603" target="_blank" >RIV/00216208:11320/23:10492603 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10470804" target="_blank" >https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10470804</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/AICS60730.2023.10470804" target="_blank" >10.1109/AICS60730.2023.10470804</a>
Alternative languages
Result language
angličtina
Original language name
Exploring Abductive Reasoning in Language Models for Data-to-Text Generation
Original language description
Abductive reasoning remains underexplored in language models despite its everyday human use, effectiveness in handling incomplete information, and use in automated planning. We present a data-to-text generation pipeline that prompts language models with abductive tasks to investigate its applicability. We show its utility in content selection, though generating a discourse plan for selected content presents challenges for non-fine-tuned language models. The three-stage pipeline allows for the deployment of more suitable models for different stages (reasoning and realization). This work highlights the potential of symbolic reasoning approaches in enhancing language models.
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
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
31st Irish Conference on Artificial Intelligence and Cognitive Science (AICS)
ISBN
979-8-3503-6021-9
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
1-4
Publisher name
IEEE
Place of publication
New York City, U.S.
Event location
Letterkenny, Ireland
Event date
Dec 7, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001195949100032