mlsanityData to 14 Oct 2026

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

arXiv 2404.02466 ↗First posted 3 Apr 2024cs.CL cs.AI cs.CEcited by 3

Not on the map. Why?

Abstract (arXiv)

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 into prompting for time-series numerical data are lacking. Therefore, this study explores various input representations, including sequences of tokens and structured formats such as HTML, LaTeX, and Python-style codes. In our experiments, we focus on the task of Market Comment Generation, which involves taking a numerical sequence of stock prices as input and generating a corresponding market comment. Contrary to our expectations, the results show that prompts resembling programming languages yield better outcomes, whereas those similar to natural languages and longer formats, such as HTML and LaTeX, are less effective. Our findings offer insights into creating effective prompts for tasks that generate text from numerical sequences.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 15 of its 34 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

15 of 34 references.

References · 15

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 343
  5. 2022In-context Examples Selection for Machine Translationcited by 172
  6. 2022Chart-to-Text: A Large-Scale Benchmark for Chart Summarizationcited by 169
  7. 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 145
  8. 2018Data-to-Text Generation with Content Selection and Planningcited by 106
  9. 2023Large language models effectively leverage document-level context for literary translation, but critical errors persistcited by 80
  10. 2023Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Methodcited by 76
  11. 2017Neural AMR: Sequence-to-Sequence Models for Parsing and Generationcited by 56
  12. 2022Graph Pre-training for AMR Parsing and Generationcited by 55
3 more
  1. 2023Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphscited by 24
  2. 2022MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generationcited by 7
  3. 2023Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translatecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025AI Analyst: Framework and Comprehensive Evaluation of Large Language Models for Financial Time Series Report Generationcited by 1
  2. 2025Decoding Open-Ended Information Seeking Goals from Eye Movements in Readingcited by 0
  3. 2026A Comparative Study of Demonstration Selection for Practical Large Language Models-based Next POI Predictioncited by 0