黑盒提示优化：无需模型训练的大语言模型对齐
Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
AI总结：
针对大语言模型对齐训练成本高、部分模型无法训练的问题，提出无需更新模型参数的黑盒提示优化BPO方法，利用人类偏好优化提示，性能优于PPO、DPO等对齐方法且可与之结合增益。
摘要：
大语言模型（LLM）已在各类应用中展现出令人瞩目的成效，但这类模型往往未能与人类意图良好对齐，这一问题被称为对齐问题，需要对模型进行额外调整。为让LLM更好地遵循用户指令，现有对齐方法主要聚焦于对模型进行进一步训练，但LLM的额外训练通常需要耗费高昂的GPU计算资源；更棘手的是，部分LLM（如GPT系列）不支持用户按需开展训练。本文提出了一种全新思路——黑盒提示优化（Black-Box Prompt Optimization, BPO）来实现对齐，核心是优化用户提示以适配LLM的输入理解能力，从而在不更新LLM参数的前提下最大程度实现用户意图。BPO利用人类偏好来优化提示，因此其作为提示优化工具的表现优于ChatGPT等LLM。此外，BPO具有模型无关性，实验结果显示，经BPO对齐的ChatGPT相较于原始版本胜率提升22%，GPT-4的胜率提升10%。值得注意的是，经BPO对齐的LLM表现能够超过通过PPO和DPO对齐的同型号模型；将BPO与PPO或DPO结合使用时，还能带来额外的性能提升。相关代码与数据集已发布于https://github.com/thu-coai/BPO。
英文摘要：
Large language models (LLMs) have shown impressive success in various applications. However, these models are often not well aligned with human intents, which calls for additional treatments on them; that is, the alignment problem. To make LLMs better follow user instructions, existing alignment methods primarily focus on further training them. However, the extra training of LLMs is usually expensive in terms of GPU computing; even worse, some LLMs are not accessible for user-demanded training, such as GPTs. In this work, we take a different perspective -- Black-Box Prompt Optimization (BPO) -- to perform alignments. The idea is to optimize user prompts to suit LLMs' input understanding, so as to best realize users' intents without updating LLMs' parameters. BPO leverages human preferences to optimize prompts, thus making it superior to LLM (e.g., ChatGPT) as a prompt engineer. Moreover, BPO is model-agnostic, and the empirical results demonstrate that the BPO-aligned ChatGPT yields a 22% increase in the win rate against its original version and 10% for GPT-4. Notably, the BPO-aligned LLMs can outperform the same models aligned by PPO and DPO, and it also brings additional performance gains when combining BPO with PPO or DPO. Code and datasets are released at https://github.com/thu-coai/BPO.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
