The paper introduces the Spider Network Filtering Framework, an interaction‑aware decision model for FDIC‑assisted distressed bank acquisitions. It encodes dependencies among five dimensions—acquisition value, regulatory protection, risk, buyer strength, and execution difficulty—into four interpretable rules, producing graph‑inspired features for a logistic model and a Pursue/Caution/Avoid decision rule. Evaluated on 55 FDIC‑assisted acquisitions from 2008‑2024, the Spider‑enhanced model achieves a mean AUC of 0.594, slightly lower than logistic (0.615) and ridge (0.632) regressions, and permutation tests show only weak evidence of performance above chance.
arXiv:2609.37223v1 Announce Type: new Abstract: Credit-risk prediction is important in banking, but a prediction alone does not explain why an applicant is risky or how it should be combined with oth...
arXiv:2607.20491v4 Announce Type: replace-cross Abstract: When a financial agent repeats its decision, how much does that tell us about the actions behind it? DFAH-Bench examines this question throug...
The study examines how different harness configurations affect a fixed large language model’s compliance with banking conduct rules. Four open‑weight models were tested across five harnesses on 156 pre‑registered retail‑banking scenarios, yielding 3,120 two‑turn episodes scored for rule violations and over‑refusals. Results show that while overall compliance rates varied modestly (87.3%–92.1%), the impact of a harness differed markedly between models, with some models’ best and worst harnesses differing by over 10 percentage points and a same‑model compliance reviewer reducing violations from 9.6% to 6.4%. whyItMatters":"The findings suggest that validating a model’s compliance requires testing the specific model‑harness pair rather than the model alone, highlighting the importance of action logs over conversation transcripts for accurate conduct assessment."
arXiv:2608. 08202v1 Announce Type: new Abstract: Data-centric curation pipelines frequently rely on model confidence scores to flag and filter noisy or mislabeled training instances.
FinRiskAtlas is a Chinese-language benchmark designed to evaluate large language models (LLMs) for financial risk review by focusing on decision‑aligned tasks rather than generic financial knowledge. It contains 9,742 instances across 53 task families, including 42 domain‑knowledge families and 11 downstream review operations defined by explicit evaluation contracts. The extended FinRisk‑Ask framework replays 680 pre‑action states from 104 professional trajectories, withholding future evidence during inference to assess evidence‑state control and request targeting. Results across 33 model configurations show that operation‑level evaluation yields distinct rankings and that knowledge‑based shortlisting can incur significant regret, while frequent use of the Ask branch does not necessarily improve evidence acquisition, highlighting gaps in broad financial capability scores.
arXiv:2606. 18479v1 Announce Type: new Abstract: Reject inference methods are widely used to mitigate survival bias in credit scoring, yet their effectiveness remains poorly understood.
arXiv:2610. 32380v1 Announce Type: new Abstract: Large language models (LLMs) can read startup pitch decks, but letting them emit investment scores directly invites score inflation, run-to-run variance and rationales that are hard to audit.
FinRED is an expert‑guided framework for generating and evaluating financial LLM red‑teaming tests. It maps global financial standards to specific threats, converts real documents into context‑rich prompts, and offers a validated rubric that reduces false negatives. The framework is deployed in South Korea’s Financial Security Institute sandbox and is gated for qualified researchers.
arXiv:2606. 19887v1 Announce Type: cross Abstract: Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks.
The Data Differentiator Framework (DDF) is a composite scoring method that evaluates candidate data assets by combining a mutual‑information redundancy penalty, a cost‑normalized marginal utility score from an ablation study, and explicit governance inputs such as trust and strategic weights. It is executed through the Strategic Data Sourcing Agent Ecosystem (SDSAE), which bypasses costly model retraining for assets that fail governance or redundancy checks. In a credit‑card fraud benchmark, only the genuinely differentiated asset passed the significance gate and received an acquisition recommendation, while a fully redundant asset scored lowest.
The study investigates whether Large Language Models (LLMs) can translate technical explanations from credit risk models into stakeholder-friendly narratives. Using Freddie Mac loan data, the authors compare standard tabular models (XGBoost + SHAP) with alternative data pipelines (GNN + GNNExplainer and a bimodal mix) and generate explanations with three LLM configurations: a small fine‑tuned Gemma 3 4B, a large fine‑tuned DeepSeek R1 70B, and a zero‑shot Gemini 2.5. Findings show that the quality of explanations is more dependent on the evidence representation than on the LLM, that narratives reliably identify influential factors but are less consistent about the direction of influence, and that credit professionals demand higher evidentiary standards than non‑professionals.
arXiv:2608. 10050v1 Announce Type: new Abstract: Small and medium-sized businesses need timely financial guidance, yet historical accounting logs record self-selected and often co-occurring business changes rather than randomized recommendations.