Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning

• URL: http://arxiv.org/abs/2603.15459v1
• Date: Mon, 16 Mar 2026 15:56:21 GMT
• Title: Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning
• Abstract summary: FinTRACE is a retrieval-first architecture that converts raw transactions into reusable feature representations.<n>Across public and industrial benchmarks, FinTRACE substantially improves low-supervision transaction analytics.
• Score: 0.3947144942254943
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Nowadays, success of financial organizations heavily depends on their ability to process digital traces generated by their clients, e.g., transaction histories, gathered from various sources to improve user modeling pipelines. As general-purpose LLMs struggle with time-distributed tabular data, production stacks still depend on specialized tabular and sequence models with limited transferability and need for labeled data. To address this, we introduce FinTRACE, a retrieval-first architecture that converts raw transactions into reusable feature representations, applies rule-based detectors, and stores the resulting signals in a behavioral knowledge base with graded associations to the objectives of downstream tasks. Across public and industrial benchmarks, FinTRACE substantially improves low-supervision transaction analytics, doubling zero-shot MCC on churn prediction performance from 0.19 to 0.38 and improving 16-shot MCC from 0.25 to 0.40. We further use FinTRACE to ground LLMs via instruction tuning on retrieved behavioral patterns, achieving state-of-the-art LLM results on transaction analytics problems.

Related papers

• MINT: A Universal Zero-Shot Predictor for Transaction Data [5.76828154035244]
  We present MINT, a framework that connects a pretrained transaction sequence encoder to a decoder-only LLM through lightweight embedding injection.<n>MINT achieves state-of-the-art predictive question-answering performance in both in-distribution and out-of-distribution questions.<n>We find that MINT achieves state-of-the-art predictive question-answering performance in both in-distribution and out-of-distribution questions.
  arXiv  Detail & Related papers  (2026-08-14T11:17:01Z)
• Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation [0.17188280334580197]
  Money laundering presents a persistent challenge for financial institutions worldwide.<n>Traditional anti-money laundering approaches mainly rely on predefined risk-based rules.<n>We present ExSTraQt, an advanced supervised learning approach to detect money laundering (or suspicious) transactions in financial datasets.
  arXiv  Detail & Related papers  (2026-04-03T09:14:39Z)
• Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs [66.63911043019294]
  Data preparation aims to denoise raw datasets, uncover cross-dataset relationships, and extract valuable insights from them.<n>This paper focuses on the use of LLM techniques to prepare data for diverse downstream tasks.<n>We introduce a task-centric taxonomy that organizes the field into three major tasks: data cleaning, standardization, error processing, imputation, data integration, and data enrichment.
  arXiv  Detail & Related papers  (2026-01-22T12:02:45Z)
• Enhancing Foundation Models in Transaction Understanding with LLM-based Sentence Embeddings [26.118375969968437]
  Large Language Models (LLMs) can address this limitation through superior semantic understanding.<n>We introduce a hybrid framework that uses LLM-generated embeddings as semantic initializations for lightweight transaction models.<n>Our approach employs multi-source data fusion to enrich merchant categorical fields and a one-word constraint principle for consistent embedding generation.
  arXiv  Detail & Related papers  (2025-12-01T23:30:17Z)
• Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM [51.21051698747157]
  We propose a self-adaptive gradient-aware data selection approach (GrADS) for supervised fine-tuning of large language models (LLMs)<n>Specifically, we design self-guided criteria that leverage the magnitude and statistical distribution of gradients to prioritize examples that contribute the most to the model's learning process.<n>Through extensive experimentation with various LLMs across diverse domains such as medicine, law, and finance, GrADS has demonstrated significant efficiency and cost-effectiveness.
  arXiv  Detail & Related papers  (2025-11-07T08:34:50Z)
• LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clients [0.6106535351521803]
  We propose LATTE, a contrastive learning framework that aligns raw event embeddings with semantic embeddings from frozen language models.<n>We experimentally show that our method outperforms state-of-the-art techniques for learning event sequence representations on real-world financial datasets.
  arXiv  Detail & Related papers  (2025-08-07T16:46:38Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning [65.23593936798662]
  We show that fine-tuning with LLM-generated data improves target task performance and reduces non-target task degradation.<n>This is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2025-01-24T08:18:56Z)
• Advancing Anomaly Detection: Non-Semantic Financial Data Encoding with LLMs [49.57641083688934]
  We introduce a novel approach to anomaly detection in financial data using Large Language Models (LLMs) embeddings. Our experiments demonstrate that LLMs contribute valuable information to anomaly detection as our models outperform the baselines.
  arXiv  Detail & Related papers  (2024-06-05T20:19:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.