Less but Better: Parameter-Efficient Fine-Tuning of Large Language Models for Personality Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915232521125888 |
|---|---|
| author | Shen, Lingzhi Long, Yunfei Cai, Xiaohao Chen, Guanming Razzak, Imran Jameel, Shoaib |
| author_facet | Shen, Lingzhi Long, Yunfei Cai, Xiaohao Chen, Guanming Razzak, Imran Jameel, Shoaib |
| contents | Personality detection automatically identifies an individual's personality from various data sources, such as social media texts. However, as the parameter scale of language models continues to grow, the computational cost becomes increasingly difficult to manage. Fine-tuning also grows more complex, making it harder to justify the effort and reliably predict outcomes. We introduce a novel parameter-efficient fine-tuning framework, PersLLM, to address these challenges. In PersLLM, a large language model (LLM) extracts high-dimensional representations from raw data and stores them in a dynamic memory layer. PersLLM then updates the downstream layers with a replaceable output network, enabling flexible adaptation to various personality detection scenarios. By storing the features in the memory layer, we eliminate the need for repeated complex computations by the LLM. Meanwhile, the lightweight output network serves as a proxy for evaluating the overall effectiveness of the framework, improving the predictability of results. Experimental results on key benchmark datasets like Kaggle and Pandora show that PersLLM significantly reduces computational cost while maintaining competitive performance and strong adaptability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05411 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Less but Better: Parameter-Efficient Fine-Tuning of Large Language Models for Personality Detection Shen, Lingzhi Long, Yunfei Cai, Xiaohao Chen, Guanming Razzak, Imran Jameel, Shoaib Computation and Language Machine Learning Personality detection automatically identifies an individual's personality from various data sources, such as social media texts. However, as the parameter scale of language models continues to grow, the computational cost becomes increasingly difficult to manage. Fine-tuning also grows more complex, making it harder to justify the effort and reliably predict outcomes. We introduce a novel parameter-efficient fine-tuning framework, PersLLM, to address these challenges. In PersLLM, a large language model (LLM) extracts high-dimensional representations from raw data and stores them in a dynamic memory layer. PersLLM then updates the downstream layers with a replaceable output network, enabling flexible adaptation to various personality detection scenarios. By storing the features in the memory layer, we eliminate the need for repeated complex computations by the LLM. Meanwhile, the lightweight output network serves as a proxy for evaluating the overall effectiveness of the framework, improving the predictability of results. Experimental results on key benchmark datasets like Kaggle and Pandora show that PersLLM significantly reduces computational cost while maintaining competitive performance and strong adaptability. |
| title | Less but Better: Parameter-Efficient Fine-Tuning of Large Language Models for Personality Detection |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2504.05411 |