Enhancing Foundation Models in Transaction Understanding with LLM-based Sentence Embeddings

TL;DR

This paper proposes a hybrid approach that leverages LLM-generated embeddings to improve transaction understanding models, balancing semantic richness with computational efficiency in financial applications.

Contribution

It introduces a novel framework combining LLM embeddings with lightweight models, enhancing semantic understanding of transaction data while maintaining operational efficiency.

Findings

Significant performance improvements on large-scale datasets

Effective multi-source data fusion for merchant fields

Robust embedding generation with noise filtering and context enrichment

Abstract

The ubiquity of payment networks generates vast transactional data encoding rich consumer and merchant behavioral patterns. Recent foundation models for transaction analysis process tabular data sequentially but rely on index-based representations for categorical merchant fields, causing substantial semantic information loss by converting rich textual data into discrete tokens. While Large Language Models (LLMs) can address this limitation through superior semantic understanding, their computational overhead challenges real-time financial deployment. We introduce a hybrid framework that uses LLM-generated embeddings as semantic initializations for lightweight transaction models, balancing interpretability with operational efficiency. Our approach employs multi-source data fusion to enrich merchant categorical fields and a one-word constraint principle for consistent embedding generation across LLM architectures. We systematically address data quality through noise filtering and context-aware enrichment. Experiments on large-scale transaction datasets demonstrate significant performance improvements across multiple transaction understanding tasks.