Verifiable Financial Enterprise Question Answering via Inference-Time Grounding and Traceability

Anubha Kabra, Katie Jooyoung Kim, Zhiwei Kou, Helene Sajer, Yimei Fan, Gabriel Martinez Vidiri


Abstract
Financial enterprise AI systems deployed in high-stakes settings require responses that are verifiable, traceable, and auditable. We introduce a modular, model- and data-agnostic inference-time control framework, together with a deployment-aware evaluation strategy for verifiable financial enterprise question answering. Our method enforces faithfulness at inference time without retraining or changes to retrieval infrastructure. We deploy our method in a production financial enterprise assistant and evaluate it using a combination of intrinsic faithfulness metrics, baseline comparisons, and real-world user feedback. Our approach improves groundedness by 29% over baselines, reduces hallucinations to near-zero levels, and achieves near-perfect document-span traceability. Together, our results demonstrate that modular pipeline design combined with detailed, deployment-aware evaluation provides a practical and effective path toward verifiable financial enterprise QA systems.
Anthology ID:
2026.fnp-1.4
Volume:
The 7th Financial Narrative Processing Workshop
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Mo El-Haj, Antonio Moreno Sandoval, Ana Garcia-Serrano, Chung-Chi Chen, Paul Rayson, Yanco Amor Torterolo Orta, Paloma Martinez, Jordi Porta
Venues:
FNP | WS
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
39–48
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-fnp-04
DOI:
10.63317/25dqodqmcsa4
Bibkey:
Cite (ACL):
Anubha Kabra, Katie Jooyoung Kim, Zhiwei Kou, Helene Sajer, Yimei Fan, and Gabriel Martinez Vidiri. 2026. Verifiable Financial Enterprise Question Answering via Inference-Time Grounding and Traceability. In The 7th Financial Narrative Processing Workshop, pages 39–48, Palma de Mallorca, Spain. European Language Resources Association (ELRA).
Cite (Informal):
Verifiable Financial Enterprise Question Answering via Inference-Time Grounding and Traceability (Kabra et al., FNP 2026)
Copy Citation: