← Search

Masayuki Kawarada

2 accepted papers

2024

Demonstration Selection Strategies for Numerical Time Series Data-to-Text

EMNLP 2024finding

Demonstration selection, the process of selecting examples used in prompts, plays a critical role in in-context learning. This paper explores demonstration selection methods for data-to-text tasks that involve numerical time series data as inputs.Previously developed demonstration selection methods…

Cited by 0SourcePDFScholar
2024

Prompting for Numerical Sequences: A Case Study on Market Comment Generation

COLING 2024main

Large language models (LLMs) have been applied to a wide range of data-to-text generation tasks, including tables, graphs, and time-series numerical data-to-text settings. While research on generating prompts for structured data such as tables and graphs is gaining momentum, in-depth investigations…