Neuro-symbolic constraint verification for LLM-driven internet finance transaction execution

Abstract

Large language model (LLM) agents cannot guarantee that their outputs satisfy the hard business rules that govern financial transactions. We present the Verifier-Actor Neuro-Symbolic Framework (VA-NSF), a dual-layer architecture that separates natural language understanding from formal constraint enforcement for internet finance transaction execution. A neural Actor parses financial instructions into a typed, schema-grounded abstract syntax tree (AST) through grammar-constrained decoding, and a symbolic Verifier evaluates each AST against Answer Set Programming (ASP) integrity constraints, issuing either a formal approval certificate or a structured violation report that drives targeted repair. On FinTxBench, a curated evaluation set of 8600 annotated financial instructions spanning three complexity tiers, VA-NSF attains 91.8% overall transaction accuracy (macro-averaged across the three tiers, with 94.7%, 91.2%, and 89.6% on the Simple, Compound, and Constrained tiers) at a constraint violation rate of at most 0.3%. It thereby outperforms four LLM baselines by 13 to 51 percentage points and reduces violations 30-fold, all within a median latency of 399 ms, of which ASP verification accounts for only 24 ms. Ablations confirm that each component contributes independently, and cross-domain experiments on payment processing, procurement, payroll, and inventory modules show at most 5.8 percentage points of degradation. All formal guarantees are relative to the fidelity of the encoded rule set, and the evaluation uses a curated benchmark with up to 80 rules; we therefore discuss explicitly the resulting limitations regarding noisy real-world language, rule-set scale, and human-escalation overhead.

Anonymous transaction amount verification system based on zero knowledge range proof
Jiawen Shi, Xiuyan Bai, Jiangjun Yuan +1
Scientific Reports1 Jul 2026Peer-reviewedCC BYFull textGeneral medicineDOAJ
Physics-consistent equation discovery for drug solubility in supercritical CO₂ through symbolic regression and domain generalization
Adel Alhowyan, Ahmad J. Obaidullah, Wael A. Mahdi
Frontiers in medicine19 Oct 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC
Internet Intervention for Functional Seizures
Lana Higson, Zhibin Chen, Genevieve Rayner +4
JAMA Neurology26 Oct 2026Peer-reviewedLicence not statedFull textPsychiatry & mental healthPMC
Symbolic transfer entropy reveals enhanced cardiac autonomic influence on cortical activity in infants with congenital heart disease
Wenjuan Luo, Haitao Liu, Tiejia Jiang +4
Scientific Reports16 Oct 2026Peer-reviewedCC BY-NC-ND 4.0Full textCardiovascular medicineCrossref
Relationship stress at workplace was associated with problem drinking patterns: a nationwide Internet-based prospective cohort study
Mami Wakabayashi, Hiroyasu Iso, Takahiro Tabuchi
Environmental Health and Preventive Medicine19 Sep 2026Peer-reviewedCC BY 4.0Full textEpidemiology & public healthJ-STAGE

Cite

BibTeX RIS

BibTeX

@article{qin2026neurosymbolic,
  title = {{Neuro-symbolic constraint verification for LLM-driven internet finance transaction execution}},
  author = {Yuxuan Qin and Minjae Rhee and Dai Teng and Changhao Zhang and Bingjie Zi},
  journal = {Scientific Reports},
  year = {2026},
  month = aug,
  doi = {10.1038/s41598-026-65233-w},
  url = {https://doi.org/10.1038/s41598-026-65233-w},
  note = {CC BY},
}

RIS

TY  - JOUR
TI  - Neuro-symbolic constraint verification for LLM-driven internet finance transaction execution
AU  - Yuxuan Qin
AU  - Minjae Rhee
AU  - Dai Teng
AU  - Changhao Zhang
AU  - Bingjie Zi
PY  - 2026
DA  - 2026/08/01
JO  - Scientific Reports
DO  - 10.1038/s41598-026-65233-w
UR  - https://doi.org/10.1038/s41598-026-65233-w
AB  - Large language model (LLM) agents cannot guarantee that their outputs satisfy the hard business rules that govern financial transactions. We present the Verifier-Actor Neuro-Symbolic Framework (VA-NSF), a dual-layer architecture that separates natural language understanding from formal constraint enforcement for internet finance transaction execution. A neural Actor parses financial instructions into a typed, schema-grounded abstract syntax tree (AST) through grammar-constrained decoding, and a symbolic Verifier evaluates each AST against Answer Set Programming (ASP) integrity constraints, issuing either a formal approval certificate or a structured violation report that drives targeted repair. On FinTxBench, a curated evaluation set of 8600 annotated financial instructions spanning three complexity tiers, VA-NSF attains 91.8% overall transaction accuracy (macro-averaged across the three tiers, with 94.7%, 91.2%, and 89.6% on the Simple, Compound, and Constrained tiers) at a constraint violation rate of at most 0.3%. It thereby outperforms four LLM baselines by 13 to 51 percentage points and reduces violations 30-fold, all within a median latency of 399 ms, of which ASP verification accounts for only 24 ms. Ablations confirm that each component contributes independently, and cross-domain experiments on payment processing, procurement, payroll, and inventory modules show at most 5.8 percentage points of degradation. All formal guarantees are relative to the fidelity of the encoded rule set, and the evaluation uses a curated benchmark with up to 80 rules; we therefore discuss explicitly the resulting limitations regarding noisy real-world language, rule-set scale, and human-escalation overhead.
SN  - 2045-2322
ER  -

Abstract

Related

Cite