In this paper, we introduce the Financial-STS task, a financial
domain-specific NLP task designed to measure the nuanced semantic similarity
between pairs of financial narratives. These narratives originate from the
financial statements of the same company but correspond to different periods,
such as year-over-year comparisons. Measuring the subtle semantic differences
between these paired narratives enables market stakeholders to gauge changes
over time in the company's financial and operational situations, which is
critical for financial decision-making. We find that existing pretrained
embedding models and LLM embeddings fall short in discerning these subtle
financial narrative shifts. To address this gap, we propose an LLM-augmented
pipeline specifically designed for the Financial-STS task. Evaluation on a
human-annotated dataset demonstrates that our proposed method outperforms
existing methods trained on classic STS tasks and generic LLM embeddings.

介绍了金融领域特定的 NLP 任务 —— 金融语义相似性（Financial-STS）任务，该任务的目的是评估金融报告对比中的细微语义差异，以帮助金融决策，发现现有的预训练嵌入模型和 LLM 嵌入不足以区分这些细微的金融故事变化，因此提出了一种 LLM 增强的针对金融 - STS 任务的流程，通过在人工标注数据集上进行评估，证明我们的方法胜过在经典 STS 任务和通用 LLM 嵌入上训练的现有方法。

超越表面相似性：检测金融叙述中微妙的语义转变

Beyond Surface Similarity: Detecting Subtle Semantic Shifts in Financial  Narratives

In this paper, we design a real-time question-answering system specifically
targeted for helping sellers get relevant material/documentation they can share
live with their customers or refer to during a call. Taking the Seismic content
repository as a relatively large scale example of a diverse dataset of sales
material, we demonstrate how LLM embeddings of sellers' queries can be matched
with the relevant content. We achieve this by engineering prompts in an
elaborate fashion that makes use of the rich set of meta-features available for
documents and sellers. Using a bi-encoder with cross-encoder re-ranker
architecture, we show how the solution returns the most relevant content
recommendations in just a few seconds even for large datasets. Our recommender
system is deployed as an AML endpoint for real-time inferencing and has been
integrated into a Copilot interface that is now deployed in the production
version of the Dynamics CRM, known as MSX, used daily by Microsoft sellers.

我们设计了一个实时问答系统，专门为帮助销售人员获取他们可以与客户共享或在电话中参考的相关材料 / 文档而开发。通过以 Seismic 内容库作为多样化数据集的相对大规模示例，我们展示了如何使用销售人员的查询的 LLM 嵌入来与相关内容匹配。通过使用具有跨编码器后处理器的双编码器体系结构，我们展示了该解决方案如何在几秒钟内返回最相关的内容推荐，即使对于大型数据集也是如此。我们的推荐系统作为一个 AML 端点用于实时推理，并已集成到称为 MSX 的 Dynamics CRM 的生产版本中，该版本每天被微软销售人员使用。

MSX Sales Copilot 中生成式 AI 的案例研究：使用实时问答系统提高销售员工生产力的内容推荐

A case study of Generative AI in MSX Sales Copilot: Improving seller  productivity with a real-time question-answering system for content  recommendation