Multi-Turn Intent Modeling for Financial Question Answering with Large Language Models
Keywords:
large language models; financial question answering; multi-turn dialogue; intent modeling; memory systems; governance; deploymentAbstract
Multi-turn financial question answering requires systems to interpret evolving user intent across sequential interactions, often involving implicit references, corrections, and shifting risk constraints. Large language models offer powerful language understanding and generation capabilities, but their deployment in financial settings introduces structural challenges related to state persistence, memory management, retrieval grounding, calibration, governance, and operational cost. This paper presents a system-level examination of multi-turn intent modeling for financial question answering. It describes intent as a dynamic construct shaped by dialogue context, user goals, and regulatory obligations. The discussion evaluates architectural options including modular state trackers, memory stores, retrieval-augmented generation, and policy layers, and it analyzes trade-offs between monolithic and component-based designs. The paper further addresses robustness and fairness concerns, including hallucination risk, distributional bias, and auditability. Deployment considerations such as latency, energy consumption, model distillation, and infrastructure sustainability are explored. The analysis emphasizes that successful financial question answering systems must balance model capability with governance controls, memory privacy, and operational resilience. The paper contributes a conceptual framework for designing multi-turn financial assistants that are not only accurate but also accountable, fair, and sustainable.
References
1. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 4171–4186.
2. Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., et al. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
3. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., et al. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
4. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., et al. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730–27744.
5. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837.
6. Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., et al. (2023). A survey of large language models. arXiv preprint arXiv:2303.18223.
7. Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., et al. (2021). On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258.
8. Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610–623.
9. Floridi, L., & Chiriatti, M. (2020). GPT-3: Its nature, scope, limits, and consequences. Minds and Machines, 30(4), 681–694.
10. Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., et al. (2023). LLaMA: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
11. Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Computing Surveys, 55(9), 1–35.
12. Yu, X. (2026). Enhancing Search Efficiency through LLM-Based User Memory Systems for Query Matching and Intent Modeling.
13. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., et al. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
14. Mitchell, M., Wu, S., Zaldivar, A., Barnes, P, Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019). Model cards for model reporting. Proceedings of the Conference on Fairness, Accountability, and Transparency, 220–229.
15. Weidinger, L., Mellor, J., Rauh, M., Griffin, C., Uesato, J., Huang, P.-S., Myatt, J., Glaese, A., Raileanu, R., Irving, G., et al. (2021). Ethical and social risks of harm from language models. arXiv preprint arXiv:2112.04359.
16. Strubell, E., Ganesh, A., & McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 3645–3650.
17. Patterson, D., Gonzalez, J., Le, Q., Liang, C., Munguia, L.-M., Rothchild, D., So, D., Texier, M., & Dean, J. (2021). Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350.
18. Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020). Scaling laws for neural language models. arXiv preprint arXiv:2001.08361.
19. Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., et al. (2022). Training compute-optimal large language models. Advances in Neural Information Processing Systems, 35, 30016–30030.
20. Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Engineering Systems and Digital Innovation
This work is licensed under a Creative Commons Attribution 4.0 International License.
