English

Augmenting In-Context-Learning in LLMs via Automatic Data Labeling and Refinement

Computation and Language 2024-10-15 v1

Abstract

It has been shown that Large Language Models' (LLMs) performance can be improved for many tasks using Chain of Thought (CoT) or In-Context Learning (ICL), which involve demonstrating the steps needed to solve a task using a few examples. However, while datasets with input-output pairs are relatively easy to produce, providing demonstrations which include intermediate steps requires cumbersome manual work. These steps may be executable programs, as in agentic flows, or step-by-step reasoning as in CoT. In this work, we propose Automatic Data Labeling and Refinement (ADLR), a method to automatically generate and filter demonstrations which include the above intermediate steps, starting from a small seed of manually crafted examples. We demonstrate the advantage of ADLR in code-based table QA and mathematical reasoning, achieving up to a 5.5% gain. The code implementing our method is provided in the Supplementary material and will be made available.

Keywords

Cite

@article{arxiv.2410.10348,
  title  = {Augmenting In-Context-Learning in LLMs via Automatic Data Labeling and Refinement},
  author = {Joseph Shtok and Amit Alfassy and Foad Abo Dahood and Eliyahu Schwartz and Sivan Doveh and Assaf Arbelle},
  journal= {arXiv preprint arXiv:2410.10348},
  year   = {2024}
}
R2 v1 2026-06-28T19:20:20.637Z