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

Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches arXiv:2512.12677v3 Announce Type: replace Abstract: 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 pretrained causal LLM and fine-tuning it on the task, using the LLM's final-token embedding as a sequence representation, and