ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization
This addresses the high cost of fine-tuning for human preference alignment in LLMs, offering a more efficient alternative, though it is incremental as it builds on existing direct preference optimization methods.
The paper tackles the problem of aligning large language models (LLMs) with human preferences without fine-tuning by proposing ICDPO, a method that uses in-context learning to borrow alignment capabilities from superior LLMs, resulting in improved performance that outperforms fine-tuning-free baselines and shows competitiveness with SFT + LoRA.
Large Language Models (LLMs) rely on Human Preference Alignment (HPA) to ensure the generation of safe content. Due to the heavy cost associated with fine-tuning, fine-tuning-free methods have emerged, typically modifying LLM decoding with external auxiliary methods. However, these methods do not essentially enhance the LLM itself. In this paper, we rethink the derivation procedures of DPO, based on which we conversely build an instant scorer using the states of the LLM before and after In-context Learning (ICL). Accordingly, we propose a novel approach called In-Context Direct Preference Optimization (ICDPO). It enables LLMs to borrow the HPA capabilities from superior LLMs with ICL, generating well-aligned responses as estimated by the aforementioned instant scorer, thereby enhancing the final performance. ICDPO can be further enhanced with a two-stage retriever and an upgraded scorer, both offering benefits. Extensive experiments show its effectiveness, particularly in outperforming two fine-tuning-free baselines, and it exhibits competitiveness with SFT + LoRA. We also conduct detailed analyses to offer comprehensive insights into ICDPO.