Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?

Xue-Yong Fu, Md Tahmid Rahman Laskar, Elena Khasanova, Cheng Chen, Shashi Tn


Abstract
Large Language Models (LLMs) have demonstrated impressive capabilities to solve a wide range of tasks without being explicitly fine-tuned on task-specific datasets. However, deploying LLMs in the real world is not trivial, as it requires substantial computing resources. In this paper, we investigate whether smaller, Compact LLMs are a good alternative to the comparatively Larger LLMs to address significant costs associated with utilizing LLMs in the real world. In this regard, we study the meeting summarization task in a real-world industrial environment and conduct extensive experiments by comparing the performance of fine-tuned compact LLMs (FLAN-T5, TinyLLaMA, LiteLLaMA, etc.) with zero-shot larger LLMs (LLaMA-2, GPT-3.5, PaLM-2). We observe that most smaller LLMs, even after fine-tuning, fail to outperform larger zero-shot LLMs in meeting summarization datasets. However, a notable exception is FLAN-T5 (780M parameters), which achieves performance on par with zero-shot Larger LLMs (from 7B to above 70B parameters), while being significantly smaller. This makes compact LLMs like FLAN-T5 a suitable cost-efficient LLM for real-world industrial deployment.
Anthology ID:
2024.naacl-industry.33
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Yi Yang, Aida Davani, Avi Sil, Anoop Kumar
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
387–394
Language:
URL:
https://aclanthology.org/2024.naacl-industry.33
DOI:
10.18653/v1/2024.naacl-industry.33
Bibkey:
Cite (ACL):
Xue-Yong Fu, Md Tahmid Rahman Laskar, Elena Khasanova, Cheng Chen, and Shashi Tn. 2024. Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track), pages 387–394, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization? (Fu et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-industry.33.pdf