Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.08733 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915019135909888 |
|---|---|
| author | Singla, Somanshu Wang, Zhen Liu, Tianyang Ashfaq, Abdullah Hu, Zhiting Xing, Eric P. |
| author_facet | Singla, Somanshu Wang, Zhen Liu, Tianyang Ashfaq, Abdullah Hu, Zhiting Xing, Eric P. |
| contents | Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve alignment without any expensive tuning or annotations, we introduce a new tuning-free approach for self-alignment, Dynamic Rewarding with Prompt Optimization (DRPO). Our approach leverages a search-based optimization framework that allows LLMs to iteratively self-improve and craft the optimal alignment instructions, all without additional training or human intervention. The core of DRPO is a dynamic rewarding mechanism, which identifies and rectifies model-specific alignment weaknesses, allowing LLMs to adapt efficiently to diverse alignment challenges. Empirical evaluations on eight recent LLMs, both open- and closed-sourced, demonstrate that DRPO significantly enhances alignment performance, with base models outperforming their SFT/RLHF-tuned counterparts. Moreover, the prompts automatically optimized by DRPO surpass those curated by human experts, further validating the effectiveness of our approach. Our findings highlight the great potential of current LLMs to achieve adaptive self-alignment through inference-time optimization, complementing tuning-based alignment methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_08733 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models Singla, Somanshu Wang, Zhen Liu, Tianyang Ashfaq, Abdullah Hu, Zhiting Xing, Eric P. Computation and Language Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve alignment without any expensive tuning or annotations, we introduce a new tuning-free approach for self-alignment, Dynamic Rewarding with Prompt Optimization (DRPO). Our approach leverages a search-based optimization framework that allows LLMs to iteratively self-improve and craft the optimal alignment instructions, all without additional training or human intervention. The core of DRPO is a dynamic rewarding mechanism, which identifies and rectifies model-specific alignment weaknesses, allowing LLMs to adapt efficiently to diverse alignment challenges. Empirical evaluations on eight recent LLMs, both open- and closed-sourced, demonstrate that DRPO significantly enhances alignment performance, with base models outperforming their SFT/RLHF-tuned counterparts. Moreover, the prompts automatically optimized by DRPO surpass those curated by human experts, further validating the effectiveness of our approach. Our findings highlight the great potential of current LLMs to achieve adaptive self-alignment through inference-time optimization, complementing tuning-based alignment methods. |
| title | Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.08733 |