On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929267243220992 |
|---|---|
| author | Wang, Xinpeng Duan, Shitong Yi, Xiaoyuan Yao, Jing Zhou, Shanlin Wei, Zhihua Zhang, Peng Xu, Dongkuan Sun, Maosong Xie, Xing |
| author_facet | Wang, Xinpeng Duan, Shitong Yi, Xiaoyuan Yao, Jing Zhou, Shanlin Wei, Zhihua Zhang, Peng Xu, Dongkuan Sun, Maosong Xie, Xing |
| contents | Big models have achieved revolutionary breakthroughs in the field of AI, but they might also pose potential concerns. Addressing such concerns, alignment technologies were introduced to make these models conform to human preferences and values. Despite considerable advancements in the past year, various challenges lie in establishing the optimal alignment strategy, such as data cost and scalable oversight, and how to align remains an open question. In this survey paper, we comprehensively investigate value alignment approaches. We first unpack the historical context of alignment tracing back to the 1920s (where it comes from), then delve into the mathematical essence of alignment (what it is), shedding light on the inherent challenges. Following this foundation, we provide a detailed examination of existing alignment methods, which fall into three categories: Reinforcement Learning, Supervised Fine-Tuning, and In-context Learning, and demonstrate their intrinsic connections, strengths, and limitations, helping readers better understand this research area. In addition, two emerging topics, personal alignment, and multimodal alignment, are also discussed as novel frontiers in this field. Looking forward, we discuss potential alignment paradigms and how they could handle remaining challenges, prospecting where future alignment will go. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04204 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models Wang, Xinpeng Duan, Shitong Yi, Xiaoyuan Yao, Jing Zhou, Shanlin Wei, Zhihua Zhang, Peng Xu, Dongkuan Sun, Maosong Xie, Xing Artificial Intelligence Computation and Language Big models have achieved revolutionary breakthroughs in the field of AI, but they might also pose potential concerns. Addressing such concerns, alignment technologies were introduced to make these models conform to human preferences and values. Despite considerable advancements in the past year, various challenges lie in establishing the optimal alignment strategy, such as data cost and scalable oversight, and how to align remains an open question. In this survey paper, we comprehensively investigate value alignment approaches. We first unpack the historical context of alignment tracing back to the 1920s (where it comes from), then delve into the mathematical essence of alignment (what it is), shedding light on the inherent challenges. Following this foundation, we provide a detailed examination of existing alignment methods, which fall into three categories: Reinforcement Learning, Supervised Fine-Tuning, and In-context Learning, and demonstrate their intrinsic connections, strengths, and limitations, helping readers better understand this research area. In addition, two emerging topics, personal alignment, and multimodal alignment, are also discussed as novel frontiers in this field. Looking forward, we discuss potential alignment paradigms and how they could handle remaining challenges, prospecting where future alignment will go. |
| title | On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2403.04204 |