Papers
arxiv:2512.12677

Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches

Published on Dec 14, 2025
Authors:
,

Abstract

Efficient fine-tuning strategies for decoder-only LLMs using 4-bit quantization and LoRA enable competitive classification performance on resource-constrained setups.

AI-generated summary

We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head to a pre-trained causal LLM and fine-tuning on the task (using the LLM's final token embedding as a sequence representation), and (2) instruction-tuning the LLM in a prompt->response format for classification. To enable single-GPU fine-tuning of models up to 8B parameters, we combine 4-bit model quantization with Low-Rank Adaptation (LoRA) for parameter-efficient training. Experiments on two datasets - a proprietary single-label dataset and the public WIPO-Alpha patent dataset (extreme multi-label classification) - show that the embedding-based method significantly outperforms the instruction-tuned method in F1-score, and is very competitive with - even surpassing - fine-tuned domain-specific models (e.g. BERT) on the same tasks. These results demonstrate that directly leveraging the internal representations of causal LLMs, along with efficient fine-tuning techniques, yields impressive classification performance under limited computational resources. We discuss the advantages of each approach while outlining practical guidelines and future directions for optimizing LLM fine-tuning in classification scenarios.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2512.12677 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2512.12677 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2512.12677 in a Space README.md to link it from this page.

Collections including this paper 1