NCL_NLP at SemEval-2024 Task 7: CoT-NumHG: A CoT-Based SFT Training Strategy with Large Language Models for Number-Focused Headline Generation

Junzhe Zhao, Yingxi Wang, Huizhi Liang, Nicolay Rusnachenko


Abstract
Headline Generation is an essential task in Natural Language Processing (NLP), where models often exhibit limited ability to accurately interpret numerals, leading to inaccuracies in generated headlines. This paper introduces CoT-NumHG, a training strategy leveraging the Chain of Thought (CoT) paradigm for Supervised Fine-Tuning (SFT) of large language models. This approach is aimed at enhancing numeral perception, interpretability, accuracy, and the generation of structured outputs. Presented in SemEval-2024 Task 7 (task 3): Numeral-Aware Headline Generation (English), this challenge is divided into two specific subtasks. The first subtask focuses on numerical reasoning, requiring models to precisely calculate and fill in the missing numbers in news headlines, while the second subtask targets the generation of complete headlines. Utilizing the same training strategy across both subtasks, this study primarily explores the first subtask as a demonstration of our training strategy. Through this competition, our CoT-NumHG-Mistral-7B model attained an accuracy rate of 94%, underscoring the effectiveness of our proposed strategy.
Anthology ID:
2024.semeval-1.40
Volume:
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
261–269
Language:
URL:
https://aclanthology.org/2024.semeval-1.40
DOI:
10.18653/v1/2024.semeval-1.40
Bibkey:
Cite (ACL):
Junzhe Zhao, Yingxi Wang, Huizhi Liang, and Nicolay Rusnachenko. 2024. NCL_NLP at SemEval-2024 Task 7: CoT-NumHG: A CoT-Based SFT Training Strategy with Large Language Models for Number-Focused Headline Generation. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 261–269, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
NCL_NLP at SemEval-2024 Task 7: CoT-NumHG: A CoT-Based SFT Training Strategy with Large Language Models for Number-Focused Headline Generation (Zhao et al., SemEval 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.semeval-1.40.pdf
Supplementary material:
 2024.semeval-1.40.SupplementaryMaterial.zip
Supplementary material:
 2024.semeval-1.40.SupplementaryMaterial.txt