Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detector

• URL: http://arxiv.org/abs/2603.04663v2
• Date: Sun, 08 Mar 2026 09:45:52 GMT
• Title: Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detector
• Abstract summary: We introduce the Verifiable Numerical Reasoning Agent (VeNRA)<n>VeNRA shifts the RAG paradigm from retrieving probabilistic text to retrieving deterministic variables via a strictly typed Universal Fact Ledger (UFL)<n>We train the Sentinel: a 3-billion SLM trained to forensically audit candidate using a single-token inference budget.
• Score: 2.950245545999729
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Standard Retrieval-Augmented Generation (RAG) architectures fail in high-stakes financial domains due to two fundamental limitations: the inherent arithmetic incompetence of Large Language Models (LLMs) and the distributional semantic conflation of dense vector retrieval (e.g., mapping "Net Income" to "Net Sales" due to contextual proximity). In deterministic domains, a 99% accuracy rate yields 0% operational trust. To achieve zero-hallucination financial reasoning, we introduce the Verifiable Numerical Reasoning Agent (VeNRA). VeNRA shifts the RAG paradigm from retrieving probabilistic text to retrieving deterministic variables via a strictly typed Universal Fact Ledger (UFL). We mathematically bound this ledger using a novel Double-Lock Grounding algorithm. Coupled with deterministic Python execution, this neuro-symbolic routing compresses systemic hallucination rates to a near-zero 1.2%. Recognising that upstream parsing anomalies inevitably occur, we introduce the VeNRA Sentinel: a 3-billion parameter SLM trained to forensically audit candidate using a single-token inference budget with optional post-hoc reasoning. To train the Sentinel, we steer away from traditional hallucination datasets in favour of Adversarial Simulation, programmatically sabotaging financial records to simulate Ecological Errors. The compact Sentinel consequently outperforms 70B+ frontier models in error detection. Through Loss Dilution phenomenon in Reverse-CoT training, we present a novel Micro-Chunking loss algorithm to stabilise gradients under extreme verdict penalisation, yielding a 28x latency speedup without sacrificing forensic rigor.

Related papers

• Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection [0.2864713389096699]
  We propose a multi-objective reinforcement learning framework to overcome class imbalance in financial anomaly detection.<n>Our approach synthesizes heterogeneous transaction features into cohesive natural-narratives, encoded by large language models.<n>It achieves superior minority-class recall compared to scalarized baselines, providing an alternative to trade bounded operational friction for financial anomaly discovery.
  arXiv  Detail & Related papers  (2026-07-10T17:39:00Z)
• Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems [3.1567687557500297]
  Narrowband interference (NBI) severely degrades frequency-division multiplexing (OFDM) systems.<n>We use a unified deep learning framework for joint NBI cancellation and robust soft demodulation.
  arXiv  Detail & Related papers  (2026-07-09T17:26:43Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback [50.89125374999765]
  We provide the first convergence guarantee for Optimistic Multiplicative Weights Update ($mathtOMWU$) in NLHF.<n>Our analysis identifies a novel marginal convergence behavior, where the probability of rarely played actions grows exponentially from exponentially small values.
  arXiv  Detail & Related papers  (2025-12-31T12:08:29Z)
• Scalable Neural Incentive Design with Parameterized Mean-Field Approximation [28.20524168049273]
  We show that when dynamics and rewards are Lipschitz, the finite-$N$ ID objective is approximated by the PMFG at rate $mathscrO(frac1sqrtN)$.<n>We further introduce our Adjoint Mean-Field Incentive Design (AMID) algorithm, which uses explicit differentiation of iterated equilibrium operators to compute gradients efficiently.
  arXiv  Detail & Related papers  (2025-10-24T13:18:54Z)
• Nondeterminism-Aware Optimistic Verification for Floating-Point Neural Networks [11.159101812934503]
  Nondeterministic Aware Optimistic verification protocol for floating-point execution on heterogeneous accelerators.<n>We implement NAO as a PyTorch-compatible runtime and a contract layer currently deployed on Holesky testnet.
  arXiv  Detail & Related papers  (2025-10-15T21:10:39Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on Large Language Models [53.36415620647177]
  Semi-structured sparsity offers a promising solution by strategically retaining $N$ elements out of every $M$ weights.<n>Existing (N:M)-compatible approaches typically fall into two categories: rule-based layerwise greedy search, which suffers from considerable errors, and gradient-driven learning, which incurs prohibitive training costs.<n>We propose a novel linear-space probabilistic framework named MaskPro, which aims to learn a prior categorical distribution for every $M$ consecutive weights and subsequently leverages this distribution to generate the (N:M)-sparsity throughout an $N$-way sampling
  arXiv  Detail & Related papers  (2025-06-15T15:02:59Z)
• Exact Certification of (Graph) Neural Networks Against Label Poisoning [50.87615167799367]
  We introduce an exact certification method for label flipping in Graph Neural Networks (GNNs)<n>We apply our method to certify a broad range of GNN architectures in node classification tasks.<n>Our work presents the first exact certificate to a poisoning attack ever derived for neural networks.
  arXiv  Detail & Related papers  (2024-11-30T17:05:12Z)
• Advancing Anomaly Detection: Non-Semantic Financial Data Encoding with LLMs [49.57641083688934]
  We introduce a novel approach to anomaly detection in financial data using Large Language Models (LLMs) embeddings. Our experiments demonstrate that LLMs contribute valuable information to anomaly detection as our models outperform the baselines.
  arXiv  Detail & Related papers  (2024-06-05T20:19:09Z)
• Explainable Fraud Detection with Deep Symbolic Classification [4.1205832766381985]
  We present Deep Classification, an extension of the Deep Symbolic Regression framework to classification problems. Because the functions are mathematical expressions that are in closed-form and concise, the model is inherently explainable both at the level of a single classification decision and the model's decision process. An evaluation on the PaySim data set demonstrates competitive predictive performance with state-of-the-art models, while surpassing them in terms of explainability.
  arXiv  Detail & Related papers  (2023-12-01T13:50:55Z)
• Transaction Fraud Detection via an Adaptive Graph Neural Network [64.9428588496749]
  We propose an Adaptive Sampling and Aggregation-based Graph Neural Network (ASA-GNN) that learns discriminative representations to improve the performance of transaction fraud detection. A neighbor sampling strategy is performed to filter noisy nodes and supplement information for fraudulent nodes. Experiments on three real financial datasets demonstrate that the proposed method ASA-GNN outperforms state-of-the-art ones.
  arXiv  Detail & Related papers  (2023-07-11T07:48:39Z)
• Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards [33.88533898709351]
  VIPeR amalgamates the randomized value function idea with the pessimism principle. It implicitly obtains pessimism by simply perturbing the offline data multiple times. It is both provably and computationally efficient in general Markov decision processes (MDPs) with neural network function approximation.
  arXiv  Detail & Related papers  (2023-02-24T17:52:12Z)
• Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes [59.61248760134937]
  We propose an efficient algorithm to achieve a regret of $tildeO(sqrtT+zeta)$. The proposed algorithm relies on the recently developed uncertainty-weighted least-squares regression from linear contextual bandit. We generalize our algorithm to the episodic MDP setting and first achieve an additive dependence on the corruption level $zeta$.
  arXiv  Detail & Related papers  (2022-12-12T15:04:56Z)
• Degeneracy is OK: Logarithmic Regret for Network Revenue Management with Indiscrete Distributions [13.310272407473809]
  We study the classical Network Revenue Management (NRM) problem with accept/reject decisions and $T$ IID arrivals.<n>We develop an online algorithm that achieves $O(log2 T)$ regret under this model.<n>We derive a second result that achieves $O(log T)$ regret under an additional assumption of second-order growth.
  arXiv  Detail & Related papers  (2022-10-14T17:52:19Z)
• Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approach [60.67748036747221]
  Implicit neural networks offer competitive performance and reduced memory consumption. They can remain brittle with respect to input adversarial perturbations. This paper proposes a theoretical and computational framework for robustness verification of implicit neural networks.
  arXiv  Detail & Related papers  (2021-12-10T03:08:55Z)
• Towards an Understanding of Benign Overfitting in Neural Networks [104.2956323934544]
  Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss. We examine how these benign overfitting phenomena occur in a two-layer neural network setting. We show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate.
  arXiv  Detail & Related papers  (2021-06-06T19:08:53Z)
• Incremental Verification of Fixed-Point Implementations of Neural Networks [0.19573380763700707]
  We develop and evaluate a novel symbolic verification framework using incremental bounded model checking (BMC), satisfiability modulo theories (SMT), and invariant inference. Our approach was able to verify and produce examples for 85.8% of 21 test cases considering different input images, and 100% of the properties related to covering methods.
  arXiv  Detail & Related papers  (2020-12-21T10:03:44Z)
• Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss [145.54544979467872]
  We consider online learning for episodically constrained Markov decision processes (CMDPs) We propose a new emphupper confidence primal-dual algorithm, which only requires the trajectories sampled from the transition model. Our analysis incorporates a new high-probability drift analysis of Lagrange multiplier processes into the celebrated regret analysis of upper confidence reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-02T05:02:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.