Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization

Authors: Xinhao Yao, Hongjin Qian, Xiaolin Hu, Gengze Xu, Wei Liu, Jian Luan, Bin Wang, Yong Liu

IJCAI 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on benchmark datasets validate the effectiveness of this approach, supporting our theoretical findings. Our analysis lays the theoretical groundwork for configuring and improving algorithms in LLMs fine-tuning.
Researcher Affiliation Collaboration 1Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China 4Beijing Academy of Artificial Intelligence 5Xiao Mi
Pseudocode No The paper describes methods like LoRA and Prefix tuning using mathematical equations and textual explanations, but does not present any structured pseudocode or algorithm blocks.
Open Source Code Yes Extended version and code, are available at https://github.com/ Xiao Mi/Efficient FT.
Open Datasets Yes Experimental results for our strategy (in Section 5) on benchmark datasets [Wang et al., 2018] and open source pre-trained models [Liu et al., 2019; AI@Meta, 2024] verify that the method can visibly influence fine-tuning efficiency.
Dataset Splits Yes We report results on development set, Pearson correlation for STSB, Matthew s correlation for Co LA, average accuracy for MNLI (matched and mismatched), and accuracy for other tasks.
Hardware Specification No The paper mentions 'limited computational resources' but does not provide any specific details about the hardware used, such as GPU or CPU models.
Software Dependencies No The paper does not provide specific software dependencies with version numbers, such as Python versions or library versions.
Experiment Setup Yes The LoRA hyperparameters were set to α = r = 8. All reported values represent the average results across 3 random seeds. ...evaluated the performance for λ values of 2, 4, and 8 (one can also determine a general optimal ratio through experiments, and even apply different settings across different layers of the model).