Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.12479 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914471167918080 |
|---|---|
| author | Wang, Shanyong Lin, Shuhang Zhao, Yining Zhu, Xi Zhang, Yongfeng |
| author_facet | Wang, Shanyong Lin, Shuhang Zhao, Yining Zhu, Xi Zhang, Yongfeng |
| contents | Recent advances in large language models (LLMs) have significantly improved the alignment of models with general human preferences. However, a major challenge remains in adapting LLMs to individual preferences, which are not only diverse but also dynamic. In this paper, we introduce a novel framework, Preference-Paired Fine-Tuning (PFT), designed to align models with contradictory and evolving individual preferences. We present a new dataset, Value Conflict Dilemma (VCD), which includes scenarios that involve conflicting human preferences, facilitating the evaluation of our approach. Our experiments demonstrate that PFT outperforms single-preference training methods, achieving up to 96.6% accuracy in multi-choice classification tasks and the highest open-ended generation score of 8.69. PFT also shows significant improvements over DPO, SFT and some traditional training methods, especially when handling conflicting preferences. Additionally, with limited user history data, models can inferring preference vector rapidly, achieving a 44.76% improvement in user-specific preference alignment in comparison to single-preference models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12479 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning Wang, Shanyong Lin, Shuhang Zhao, Yining Zhu, Xi Zhang, Yongfeng Computation and Language Recent advances in large language models (LLMs) have significantly improved the alignment of models with general human preferences. However, a major challenge remains in adapting LLMs to individual preferences, which are not only diverse but also dynamic. In this paper, we introduce a novel framework, Preference-Paired Fine-Tuning (PFT), designed to align models with contradictory and evolving individual preferences. We present a new dataset, Value Conflict Dilemma (VCD), which includes scenarios that involve conflicting human preferences, facilitating the evaluation of our approach. Our experiments demonstrate that PFT outperforms single-preference training methods, achieving up to 96.6% accuracy in multi-choice classification tasks and the highest open-ended generation score of 8.69. PFT also shows significant improvements over DPO, SFT and some traditional training methods, especially when handling conflicting preferences. Additionally, with limited user history data, models can inferring preference vector rapidly, achieving a 44.76% improvement in user-specific preference alignment in comparison to single-preference models. |
| title | Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.12479 |