面向无监督检索的时间偏好优化
Temporal Preference Optimization for Unsupervised Retrieval
AI总结:
提出TPOUR方法,通过时间检索偏好优化(TRPO)和可学习时间嵌入插值,使无监督稠密检索器能捕捉时间相关性,在时间信息检索任务上超越有监督和无监督基线。
摘要:
无监督稠密检索器通过对比学习从无标签文档中学习语义相似性,从而提供可扩展性,但它们难以捕捉时间相关性,会检索到语义相关但时间错位的文档——当文档集合跨越多个时间段时(例如,针对“2019年的总统是谁?”检索2018-2025年的文档会引入时间歧义),这是一个重要方面。现有方法依赖于带有显式时间戳的有监督训练,但这并不总是可行的。我们提出TPOUR(面向无监督检索器的时间偏好优化),它使用我们新颖的训练方法时间检索偏好优化(TRPO)。TRPO在时间维度上重新诠释偏好学习,引导检索器偏向时间对齐的文档。TPOUR进一步通过在学习到的时间嵌入中进行插值,泛化到未见的时间段,实现连续的时间对齐。在时间信息检索(T-IR)实验上,TPOUR优于无监督和有监督基线。与Qwen-Embedding-8B相比,尽管规模小约72.7倍,TPOUR Contriever在显式查询上的平均nDCG@5提高了+4.04(+12.15%),在隐式查询上提高了+4.98(+15.21%)。我们的代码可在以下网址获取:https://this URL。
英文摘要:
Unsupervised dense retrievers offer scalability by learning semantic similarity from unlabeled documents via contrastive learning, but they struggle to capture the temporal relevance, retrieving semantically related but temporally misaligned documents-an important aspect when a document collection spans multiple time periods (e.g., retrieving documents from 2018-2025 for "Who is the president in 2019?" introduces temporal ambiguity). Existing methods rely on supervised training with explicit timestamps, which are not always feasible. We propose TPOUR (Temporal Preference Optimization for Unsupervised Retriever), which uses our novel training method Temporal Retrieval Preference Optimization (TRPO). TRPO reinterprets preference learning in the temporal dimension, guiding the retriever to favor temporally aligned documents. TPOUR further generalizes to unseen time periods via interpolation in a learned time embedding, enabling continuous temporal alignment. Experiments on temporal information retrieval (T-IR), TPOUR outperforms both unsupervised and supervised baselines. Compared to Qwen-Embedding-8B, despite being about 72.7x smaller, TPOUR Contriever improves average nDCG@5 by +4.04 (+12.15%) on explicit and +4.98 (+15.21%) on implicit queries. We provide our code at https://github.com/agwaBom/TPOUR.
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。