# Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning

arXiv: https://arxiv.org/abs/2603.15459 · HTML: https://mlsanity.com/paper/2603.15459/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 15 of its 47 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 15 of 15)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [FinGPT: Open-Source Financial Large Language Models](https://mlsanity.com/paper/2306.06031/) (2023)
- [A Survey on Knowledge-Oriented Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.10677/) (2025)
- [LightAutoML: AutoML Solution for a Large Financial Services Ecosystem](https://mlsanity.com/paper/2109.01528/) (2021)
- [CatBoost: unbiased boosting with categorical features](https://mlsanity.com/paper/1706.09516/) (2017)
- [OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models](https://mlsanity.com/paper/2412.15235/) (2024)
- [The Mighty ToRR: A Benchmark for Table Reasoning and Robustness](https://mlsanity.com/paper/2502.19412/) (2025)
- [TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning](https://mlsanity.com/paper/2512.20312/) (2025)
- [RADAR: Benchmarking Language Models on Imperfect Tabular Data](https://mlsanity.com/paper/2506.08249/) (2025)
- [ARMS: Automated rules management system for fraud detection](https://mlsanity.com/paper/2002.06075/) (2020)

## Built on by (most cited first, 2 of 2)

- [TabPFN-3: Technical Report](https://mlsanity.com/paper/2605.13986/) (2026)
- [User-Centric Modeling of Transactional Sequences with Explainable State Space Models](https://mlsanity.com/paper/2607.20228/) (2026)

## Abstract (arXiv)

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.