Syntriever：如何利用大语言模型（LLM）的合成数据训练检索器
Syntriever: How to Train Your Retriever with Synthetic Data from LLMs
AI总结：
针对黑盒LLM无法提供输出概率导致现有蒸馏方法失效的问题，提出Syntriever两阶段训练框架，通过LLM合成并验证数据、用聚类损失训练检索器及部分Plackett-Luce排序对齐偏好，在多领域基准nDCG@K上获最优性能。
摘要：
大语言模型（LLM）推动了许多人工智能应用的进步。最近，有人尝试将LLM的海量知识蒸馏到信息检索系统中。这些蒸馏方法大多使用LLM的输出概率，但最新的黑盒LLM无法提供这些概率。我们提出Syntriever，一种利用黑盒LLM合成数据训练检索器的框架。Syntriever包含两个阶段：首先是蒸馏阶段，针对给定查询，利用思维链合成相关、看似不相关的段落及增强查询；让LLM自我验证合成数据是否存在幻觉，随后用聚类相关段落嵌入的损失函数训练检索器。其次是对齐阶段，将检索器与LLM的偏好对齐；提出部分Plackett-Luce排序的偏好建模方法，通过正则化防止模型过度偏离蒸馏阶段训练的结果。实验表明，Syntriever在多领域基准数据集的nDCG@K指标上达到了最先进性能。代码可在https://github.com/kmswin1/Syntriever获取。
英文摘要：
LLMs have boosted progress in many AI applications. Recently, there were attempts to distill the vast knowledge of LLMs into information retrieval systems. Those distillation methods mostly use output probabilities of LLMs which are unavailable in the latest black-box LLMs. We propose Syntriever, a training framework for retrievers using synthetic data from black-box LLMs. Syntriever consists of two stages. Firstly in the distillation stage, we synthesize relevant and plausibly irrelevant passages and augmented queries using chain-of-thoughts for the given queries. LLM is asked to self-verify the synthetic data for possible hallucinations, after which retrievers are trained with a loss designed to cluster the embeddings of relevant passages. Secondly in the alignment stage, we align the retriever with the preferences of LLMs. We propose a preference modeling called partial Plackett-Luce ranking to learn LLM preferences with regularization which prevents the model from deviating excessively from that trained in the distillation stage. Experiments show that Syntriever achieves state-of-the-art performances on benchmark datasets from various domains in nDCG@$K$. The code is available at \href{https://github.com/kmswin1/Syntriever}{https://github.com/kmswin1/Syntriever}.
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。
