Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.17003 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915272207630336 |
|---|---|
| author | Guan, Jian Wu, Junfei Li, Jia-Nan Cheng, Chuanqi Wu, Wei |
| author_facet | Guan, Jian Wu, Junfei Li, Jia-Nan Cheng, Chuanqi Wu, Wei |
| contents | Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their transition to real-world applications reveals a critical limitation: the inability to adapt to individual preferences while maintaining alignment with universal human values. Current alignment techniques adopt a one-size-fits-all approach that fails to accommodate users' diverse backgrounds and needs. This paper presents the first comprehensive survey of personalized alignment-a paradigm that enables LLMs to adapt their behavior within ethical boundaries based on individual preferences. We propose a unified framework comprising preference memory management, personalized generation, and feedback-based alignment, systematically analyzing implementation approaches and evaluating their effectiveness across various scenarios. By examining current techniques, potential risks, and future challenges, this survey provides a structured foundation for developing more adaptable and ethically-aligned LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17003 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications Guan, Jian Wu, Junfei Li, Jia-Nan Cheng, Chuanqi Wu, Wei Computation and Language Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their transition to real-world applications reveals a critical limitation: the inability to adapt to individual preferences while maintaining alignment with universal human values. Current alignment techniques adopt a one-size-fits-all approach that fails to accommodate users' diverse backgrounds and needs. This paper presents the first comprehensive survey of personalized alignment-a paradigm that enables LLMs to adapt their behavior within ethical boundaries based on individual preferences. We propose a unified framework comprising preference memory management, personalized generation, and feedback-based alignment, systematically analyzing implementation approaches and evaluating their effectiveness across various scenarios. By examining current techniques, potential risks, and future challenges, this survey provides a structured foundation for developing more adaptable and ethically-aligned LLMs. |
| title | A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.17003 |