Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling

Subhendu Khatuya, Rajdeep Mukherjee, Akash Ghosh, Manjunath Hegde, Koustuv Dasgupta, Niloy Ganguly, Saptarshi Ghosh, Pawan Goyal


Abstract
We study the problem of automatically annotating relevant numerals (GAAP metrics) occurring in the financial documents with their corresponding XBRL tags. Different from prior works, we investigate the feasibility of solving this extreme classification problem using a generative paradigm through instruction tuning of Large Language Models (LLMs). To this end, we leverage metric metadata informationto frame our target outputs while proposing a parameter efficient solution for the task using LoRA. We perform experiments on two recently released financial numeric labeling datasets. Our proposed model, **FLAN-FinXC**, achieves new state-of-the-art performances on both the datasets, outperforming several strong baselines. We explain the better scores of our proposed model by demonstrating its capability for zero-shot as well as the least frequently occurring tags. Also, even when we fail to predict the XBRL tags correctly, our generated output has substantial overlap with the ground-truth in majority of the cases.
Anthology ID:
2024.naacl-long.410
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7384–7396
Language:
URL:
https://aclanthology.org/2024.naacl-long.410
DOI:
Bibkey:
Cite (ACL):
Subhendu Khatuya, Rajdeep Mukherjee, Akash Ghosh, Manjunath Hegde, Koustuv Dasgupta, Niloy Ganguly, Saptarshi Ghosh, and Pawan Goyal. 2024. Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 7384–7396, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling (Khatuya et al., NAACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2024.naacl-long.410.pdf
Copyright:
 2024.naacl-long.410.copyright.pdf