Recently, a novel generative retrieval (GR) paradigm has been proposed, where a single sequence-to-sequence model is learned to directly generate a list of relevant document identifiers (docids) given a query. Existing GR models commonly employ maximum likelihood estimation (MLE) for optimization: This involves maximizing the likelihood of a single relevant docid given an input query, with the assumption that the likelihood for each docid is independent of the other docids in the list. We refer to these models as the pointwise approach in this article. While the pointwise approach has been shown to be effective in the context of GR, it is considered sub-optimal due to its disregard for the fundamental principle that ranking involves making predictions about lists. In this article, we address this limitation by introducing an alternative listwise approach, which empowers the GR model to optimize the relevance at the docid list level. Specifically, we view the generation of a ranked docid list as a sequence learning process: At each step, we learn a subset of parameters that maximizes the corresponding generation likelihood of the ith docid given the (preceding) top i-1 docids. To formalize the sequence learning process, we design a positional conditional probability for GR. To alleviate the potential impact of beam search on the generation quality during inference, we perform relevance calibration on the generation likelihood of model-generated docids according to relevance grades. We conduct extensive experiments on representative binary and multi-graded relevance datasets. Our empirical results demonstrate that our method outperforms state-of-the-art GR baselines in terms of retrieval performance.

最近，提出了一种新颖的生成检索（GR）范例，其中学习单个序列到序列模型以直接生成给定查询的相关文档标识符（docids）列表。现有的 GR 模型通常采用最大似然估计 (MLE) 进行优化：这涉及在给定输入查询的情况下最大化单个相关 docid 的似然性，并假设每个 docid 的似然性独立于列表中的其他 docid。在本文中，我们将这些模型称为逐点方法。虽然逐点方法已被证明在 GR 背景下是有效的，但由于它忽视了排名涉及对列表进行预测的基本原则，因此被认为是次优的。在本文中，我们通过引入另一种列表方法来解决此限制，该方法使 GR 模型能够优化文档列表级别的相关性。具体来说，我们将排序的 docid 列表的生成视为一个序列学习过程：在每一步，我们学习一个参数子集，在给定（前面的）前i -1 docid 的情况下，最大化第i个 docid 的相应生成可能性。为了形式化序列学习过程，我们设计了 GR 的位置条件概率。为了减轻推理过程中波束搜索对生成质量的潜在影响，我们根据相关性等级对模型生成的docid的生成可能性进行相关性校准。我们对代表性的二进制和多级相关性数据集进行了广泛的实验。我们的实证结果表明，我们的方法在检索性能方面优于最先进的 GR 基线。