Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khatuya, Subhendu, Naidu, Shashwat, Ghosh, Saptarshi, Goyal, Pawan, Ganguly, Niloy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915400046870528
author Khatuya, Subhendu
Naidu, Shashwat
Ghosh, Saptarshi
Goyal, Pawan
Ganguly, Niloy
author_facet Khatuya, Subhendu
Naidu, Shashwat
Ghosh, Saptarshi
Goyal, Pawan
Ganguly, Niloy
contents The explosion of textual data has made manual document classification increasingly challenging. To address this, we introduce a robust, efficient domain-agnostic generative model framework for multi-label text classification. Instead of treating labels as mere atomic symbols, our approach utilizes predefined label descriptions and is trained to generate these descriptions based on the input text. During inference, the generated descriptions are matched to the pre-defined labels using a finetuned sentence transformer. We integrate this with a dual-objective loss function, combining cross-entropy loss and cosine similarity of the generated sentences with the predefined target descriptions, ensuring both semantic alignment and accuracy. Our proposed model LAGAMC stands out for its parameter efficiency and versatility across diverse datasets, making it well-suited for practical applications. We demonstrate the effectiveness of our proposed model by achieving new state-of-the-art performances across all evaluated datasets, surpassing several strong baselines. We achieve improvements of 13.94% in Micro-F1 and 24.85% in Macro-F1 compared to the closest baseline across all datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06806
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification
Khatuya, Subhendu
Naidu, Shashwat
Ghosh, Saptarshi
Goyal, Pawan
Ganguly, Niloy
Computation and Language
Artificial Intelligence
Machine Learning
The explosion of textual data has made manual document classification increasingly challenging. To address this, we introduce a robust, efficient domain-agnostic generative model framework for multi-label text classification. Instead of treating labels as mere atomic symbols, our approach utilizes predefined label descriptions and is trained to generate these descriptions based on the input text. During inference, the generated descriptions are matched to the pre-defined labels using a finetuned sentence transformer. We integrate this with a dual-objective loss function, combining cross-entropy loss and cosine similarity of the generated sentences with the predefined target descriptions, ensuring both semantic alignment and accuracy. Our proposed model LAGAMC stands out for its parameter efficiency and versatility across diverse datasets, making it well-suited for practical applications. We demonstrate the effectiveness of our proposed model by achieving new state-of-the-art performances across all evaluated datasets, surpassing several strong baselines. We achieve improvements of 13.94% in Micro-F1 and 24.85% in Macro-F1 compared to the closest baseline across all datasets.
title Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.06806