Query Expansion in the Age of Pre-Trained and Large Language Models: A Comprehensive Survey

MCML Authors

Ercong Nie

Dr.

* Former Member

→ Group Hinrich Schütze
 Computational Linguistics

Abstract

As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning, which is widely used to reduce resource requirements. However, decreasing the rank encounters challenges with limited representational capacity when compared to full parameter fine-tuning. We present textbf{SMoA}, a high-rank Structured MOdulation Adapter that uses fewer trainable parameters while maintaining a higher rank, thereby improving the model's representational capacity and offering improved performance potential. The core idea is to freeze the original pretrained weights and selectively amplify or suppress important features of the original weights across multiple subspaces. The subspace mechanism provides an efficient way to increase the capacity and complexity of a model. We conduct both theoretical analyses and empirical studies on various tasks. Experiment results show that SMoA outperforms LoRA and its variants on 10 tasks, with extensive ablation studies validating its effectiveness.

article LLZ+26b

---

ACM Transactions on Information Systems

44.5. Jul. 2026.

---

Authors

M. Li • X. Lv • J. Zou • T. Chen • C. Zhang • S. An • E. Nie • G. Zhou

---

Links

DOI GitHub

---

Research Area

 B2 | Natural Language Processing