mlsanityData to 14 Oct 2026

PersonaLedger: Generating Realistic Financial Transactions with Persona Conditioned LLMs and Rule Grounded Feedback

arXiv 2601.03149 ↗First posted 6 Jan 2026cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Strict privacy regulations limit access to real transaction data, slowing open research in financial AI. Synthetic data can bridge this gap, but existing generators do not jointly achieve behavioral diversity and logical groundedness. Rule-driven simulators rely on hand-crafted workflows and shallow stochasticity, which miss the richness of human behavior. Learning-based generators such as GANs capture correlations yet often violate hard financial constraints and still require training on private data. We introduce PersonaLedger, a generation engine that uses a large language model conditioned on rich user personas to produce diverse transaction streams, coupled with an expert configurable programmatic engine that maintains correctness. The LLM and engine interact in a closed loop: after each event, the engine updates the user state, enforces financial rules, and returns a context aware "nextprompt" that guides the LLM toward feasible next actions. With this engine, we create a public dataset of 30 million transactions from 23,000 users and a benchmark suite with two tasks, illiquidity classification and identity theft segmentation. PersonaLedger offers a realistic, privacy preserving resource that supports rigorous evaluation of forecasting and anomaly detection models. PersonaLedger offers the community a rich, realistic, and privacy preserving resource -- complete with code, rules, and generation logs -- to accelerate innovation in financial AI and enable rigorous, reproducible evaluation.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 53 references that are in the map. First posted on arXiv 6 Jan 2026.

Builds on

34 of 53 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  5. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  6. 2020Reformer: The Efficient Transformercited by 1,668
  7. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  8. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  9. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  10. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  11. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  12. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 239
22 more
  1. 2024Tool Learning with Large Language Models: A Surveycited by 223
  2. 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agentscited by 218
  3. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 197
  4. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 160
  5. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 148
  6. 2022FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecastingcited by 147
  7. 2023User Behavior Simulation with Large Language Model based Agentscited by 140
  8. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 132
  9. 2020Tabular Transformers for Modeling Multivariate Time Seriescited by 77
  10. 2023Realistic Synthetic Financial Transactions for Anti-Money Laundering Modelscited by 50
  11. 2024GenSim: A General Social Simulation Platform with Large Language Model based Agentscited by 50
  12. 2023TabuLa: Harnessing Language Models for Tabular Data Synthesiscited by 42
  13. 2025Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systemscited by 32
  14. 2023FATA-Trans: Field And Time-Aware Transformer for Sequential Tabular Datacited by 14
  15. 2025PUB: An LLM-Enhanced Personality-Driven User Behaviour Simulator for Recommender System Evaluationcited by 12
  16. 2019Synthesizing Credit Card Transactionscited by 10
  17. 2025Can Generative Agent-Based Modeling Replicate the Friendship Paradox in Social Media Simulations?cited by 10
  18. 2024Simulating the Economic Impact of Rationality through Reinforcement Learning and Agent-Based Modellingcited by 5
  19. 2024Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systemscited by 5
  20. 2025Persona-Based Synthetic Data Generation Using Multi-Stage Conditioning with Large Language Models for Emotion Recognitioncited by 5
  21. 2024Tax Credits and Household Behavior: The Roles of Myopic Decision-Making and Liquidity in a Simulated Economycited by 3
  22. 2025LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systemscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Evaluating LLM Simulators as Differentially Private Data Generatorscited by 0