Intent-Preserving Neuro-Symbolic Repair for Safe LLM-Driven Financial Transactions
DOI:
https://doi.org/10.54097/aeq3sg57Keywords:
Answer set programming, LLM agents, Neuro-symbolic AI, Constrained repair, Intent preservation, Financial transactionsAbstract
Verifier-guided large language model (LLM) agents can certify that an executed payment satisfies a platform's business rules, yet the certificate says nothing about whether the payment is still the one the customer asked for. When a verifier rejects a command and returns a violation report, the LLM repair step can restore compliance by changing the recipient, the currency or the funding account, producing a rule-compliant but unintended transaction. We call this failure repair-induced intent drift and propose Intent-Preserving Repair (IPR), a neuro-symbolic execution scheme that anchors every user-facing field of the parsed command to evidence in the utterance and computes repairs with answer set programming: anchored fields become fixed facts, only defaulted and procedural fields are searchable, and lexicographic weak constraints select the least intrusive change. When no intent-preserving repair exists, a relaxation program returns a minimum set of conflicting rules that drives a targeted clarification instead of an execution. Building on the Verifier–Actor architecture of VA-NSF, we evaluate on SGD-Fin, 607 real banking and payment dialogues from the Schema-Guided Dialogue corpus paired with seeded platform states and nine business rules. On 296 instances with a grammar-constrained Qwen2.5-0.5B Actor, LLM repair in a re-implemented VA-NSF loop produced intent-mismatched commits for 32.1% of the requests, and 34.6% of its repaired commits on correctly parsed requests changed a user-stated field. IPR raised safe task success from 60.5% to 82.4% (p < 10⁻¹⁹), produced no drifted repair, and needed 1.15 instead of 2.49 LLM calls per request.
Downloads
References
[1] Liu, X., Yu, H., Zhang, H., Xu, Y., Lei, X., Lai, H., Gu, Y., Ding, H., Men, K., Yang, K., Zhang, S., Deng, X., Zeng, A., Du, Z., Zhang, C., Shen, S., Zhang, T., Su, Y., Sun, H., … & Tang, J. (2024). AgentBench: Evaluating LLMs as agents. In Proceedings of the International Conference on Learning Representations (ICLR).
[2] Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023). Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36, 68539-68551.
[3] Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., Qian, B., Zhao, S., Hong, L., Tian, R., Xie, R., Zhou, J., Gerstein, M., Li, D., Liu, Z., & Sun, M. (2024). ToolLLM: Facilitating large language models to master 16000+ real-world APIs. In Proceedings of the International Conference on Learning Representations (ICLR).
[4] Wang, J., Liu, J., Ge, Y., & Jiang, B. (2023). Risk-aware ensemble learning for credit default prediction under economic uncertainty. World Journal of Economics and Business Research, 1(1), 18-32.
[5] Yang, H., Liu, X.-Y., & Wang, C. D. (2023). FinGPT: Open-source financial large language models. arXiv, arXiv:2306.06031. https://doi.org/10.48550/arXiv.2306.06031
[6] Ruan, Y., Dong, H., Wang, A., Pitis, S., Zhou, Y., Ba, J., Dubois, Y., Maddison, C. J., & Hashimoto, T. (2024). Identifying the risks of LM agents with an LM-emulated sandbox. In Proceedings of the International Conference on Learning Representations (ICLR).
[7] Qin, Y., Rhee, M., Teng, D., Zhang, C., & Zi, B. (2026). Neuro-symbolic constraint verification for LLM-driven internet finance transaction execution. Scientific Reports, 16, Article 65233. https://doi.org/10.1038/s41598-026-65233-w
[8] Structuring transactions to evade reporting requirement prohibited, 31 U.S.C. § 5324.
[9] Smith, E. K., Barr, E. T., Le Goues, C., & Brun, Y. (2015). Is the cure worse than the disease? Overfitting in automated program repair. In Proceedings of the 10th Joint Meeting on Foundations of Software Engineering (ESEC/FSE) (pp. 532-543). ACM. https://doi.org/10.1145/2786805.2786825
[10] Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., Alon, U., Dziri, N., Prabhumoye, S., Yang, Y., Gupta, S., Majumder, B. P., Hermann, K., Welleck, S., Yazdanbakhsh, A., & Clark, P. (2023). Self-Refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems, 36, 46534-46594.
[11] Huang, J., Chen, X., Mishra, S., Zheng, H. S., Yu, A. W., Song, X., & Zhou, D. (2024). Large language models cannot self-correct reasoning yet. In Proceedings of the International Conference on Learning Representations (ICLR).
[12] Kamoi, R., Zhang, Y., Zhang, N., Han, J., & Zhang, R. (2024). When can LLMs actually correct their own mistakes? A critical survey of self-correction of LLMs. Transactions of the Association for Computational Linguistics, 12, 1417-1440. https://doi.org/10.1162/tacl_a_00713
[13] Teng, D. (2025). RSRBench: Reproducibility and performance benchmarking for regional seismic risk workflows. Academic Journal of Architecture and Civil Engineering, 3(1), 40-52.
[14] Pan, L., Albalak, A., Wang, X., & Wang, W. Y. (2023). Logic-LM: Empowering large language models with symbolic solvers for faithful logical reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2023 (pp. 3806-3824). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-emnlp.248
[15] Olausson, T. X., Gu, A., Lipkin, B., Zhang, C., Solar-Lezama, A., Tenenbaum, J. B., & Levy, O. (2023). LINC: A neurosymbolic approach for logical reasoning by combining language models with first-order logic provers. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 5153-5176). Association for Computational Linguistics.
[16] Yang, Z., Ishay, A., & Lee, J. (2020). NeurASP: Embracing neural networks into answer set programming. In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI) (pp. 1755-1762). https://doi.org/10.24963/ijcai.2020/243
[17] Ishay, A., Yang, Z., & Lee, J. (2023). Leveraging large language models to generate answer set programs. In Proceedings of the 20th International Conference on Principles of Knowledge Representation and Reasoning (KR) (pp. 374-383). https://doi.org/10.24963/kr.2023/37
[18] Willard, B. T., & Louf, R. (2023). Efficient guided generation for large language models. arXiv, arXiv:2307.09702. https://doi.org/10.48550/arXiv.2307.09702
[19] Geng, S., Josifoski, M., Peyrard, M., & West, R. (2023). Grammar-constrained decoding for structured NLP tasks without finetuning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 10932-10952). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.emnlp-main.674
[20] Zhou, F. (2026). Moment-constrained side-force allocation for wind-assisted merchant ships: Hydrodynamic performance of retractable anti-leeway fins and flap rudders. Innovation and Technology Studies, 3(1), 27-41.
[21] Arenas, M., Bertossi, L., & Chomicki, J. (1999). Consistent query answers in inconsistent databases. In Proceedings of the 18th ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems (PODS) (pp. 68-79). ACM. https://doi.org/10.1145/303976.303983
[22] Wijsen, J. (2005). Database repairing using updates. ACM Transactions on Database Systems, 30(3), 722-768.
[23] Gelfond, M., & Lifschitz, V. (1988). The stable model semantics for logic programming. In Proceedings of the 5th International Conference and Symposium on Logic Programming (pp. 1070-1080).
[24] Brewka, G., Eiter, T., & Truszczyński, M. (2011). Answer set programming at a glance. Communications of the ACM, 54(12), 92-103. https://doi.org/10.1145/2043174.2043195
[25] Gebser, M., Kaminski, R., Kaufmann, B., & Schaub, T. (2019). Multi-shot ASP solving with clingo. Theory and Practice of Logic Programming, 19(1), 27-82. https://doi.org/10.1017/S1471068418000054
[26] Qwen Team, Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., Dong, G., Wei, H., Lin, H., Tang, J., Wang, J., Yang, J., Tu, J., Zhang, J., Ma, J., … & Zhou, Z. (2024). Qwen2.5 technical report. arXiv, arXiv:2412.15115. https://doi.org/10.48550/arXiv.2412.15115
[27] Wang, J., Ge, Y., Liu, J., & Jiang, B. (2024). Early warning of liquidity stress in U.S. banks with seasonally aligned frailty hazards and delayed-feedback conformal alarms. Journal of Trends in Finance and Economics, 1(1), 85-100.
[28] Yue, X., Yang, J., & Liu, W. (2026). FRAUDDEBATE-AGENT: A multi-agent LLM framework with an evidence-based debate mechanism for financial statement fraud detection. Mathematics, 14(15), Article 2695. https://doi.org/10.3390/math14152695
[29] Yang, J.-S., Zeng, Z., & Shen, Z. (2025). Neural-symbolic dual-indexing architectures for scalable retrieval-augmented generation. IEEE Access, 13, 1-15. https://doi.org/10.1109/ACCESS.2025.3638761
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Computing and Electronic Information Management
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
