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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Khatuya, Subhendu, Mukherjee, Rajdeep, Ghosh, Akash, Hegde, Manjunath, Dasgupta, Koustuv, Ganguly, Niloy, Ghosh, Saptarshi, Goyal, Pawan
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909202950127616
author Khatuya, Subhendu
Mukherjee, Rajdeep
Ghosh, Akash
Hegde, Manjunath
Dasgupta, Koustuv
Ganguly, Niloy
Ghosh, Saptarshi
Goyal, Pawan
author_facet Khatuya, Subhendu
Mukherjee, Rajdeep
Ghosh, Akash
Hegde, Manjunath
Dasgupta, Koustuv
Ganguly, Niloy
Ghosh, Saptarshi
Goyal, Pawan
contents 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 information to 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06671
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling
Khatuya, Subhendu
Mukherjee, Rajdeep
Ghosh, Akash
Hegde, Manjunath
Dasgupta, Koustuv
Ganguly, Niloy
Ghosh, Saptarshi
Goyal, Pawan
Computation and Language
Computational Engineering, Finance, and Science
Machine Learning
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 information to 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.
title Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling
topic Computation and Language
Computational Engineering, Finance, and Science
Machine Learning
url https://arxiv.org/abs/2405.06671