FinRiskAtlas is introduced, a Chinese-language benchmark that evaluates financial LLMs along two complementary dimensions: operation execution under fixed evidence states and evidence-state control under evolving review conditions, and shows that broad financial capability scores do not fully capture where models are reliable in professional workflows.
Abstract
Deploying large language models for professional financial review requires more than measuring general financial competence: models must perform the specific review operation required by a workflow and determine whether available evidence is sufficient for a defensible decision. Existing financial benchmarks cover knowledge, reasoning, compliance, and professional tasks, but their evaluation units are often organized around datasets or task formulations rather than the decisions that deployed systems support. We introduce FinRiskAtlas, a Chinese-language benchmark that evaluates financial LLMs along two complementary dimensions: operation execution under fixed evidence states and evidence-state control under evolving review conditions. The static benchmark contains 9,742 instances across 53 task families, including 42 Domain Knowledge families and eleven downstream review operations defined by explicit evaluation contracts. FinRisk-Ask extends this framework through offline replay of 680 pre-action states from 104 de-identified professional trajectories, withholding future evidence during inference and using it only to construct expert-verified evidence targets. Across 33 model configurations, operation-level evaluation yields non-redundant rankings (mean pairwise Spearman correlation 0.42 across downstream operations), and knowledge-based shortlisting can incur up to 18.01 points of regret on individual operations. FinRisk-Ask further shows that entering the Ask branch more frequently does not necessarily improve request targeting or end-to-end evidence acquisition. These results show that broad financial capability scores do not fully capture where models are reliable in professional workflows, motivating evaluation units aligned with the decisions and evidence states that deployed systems must support.
Large Language Models (LLMs) have shown strong potential in financial reasoning, but existing benchmarks often evaluate domain knowledge, numerical reasoning, long-context understanding, and tool use in separate settings. This limits their ability to assess realistic professional workflows that require auditable, context-grounded, and tool-executable decisions. We introduce \textbf{INS-ActBench}, a comprehensive benchmark for evaluating professional actuarial capability in LLMs. INS-ActBench contains 12,050 Q\&A pairs from public exams and sample questions released by 16 actuarial associations. It covers three subsets: \textbf{INS-Act-Know} for standardized actuarial knowledge, \textbf{INS-Act-Case} for long-context insurance case reasoning, and \textbf{INS-Act-Practice} for spreadsheet and R-code tasks with verifiable numerical outputs. Experiments on nine representative LLMs and human actuarial experts reveal a clear capability boundary: frontier LLMs perform strongly on standardized knowledge, but remain much weaker in case reasoning, tool-based workflows, and jurisdiction-sensitive practice. INS-ActBench provides a reproducible foundation for developing actuarial LLMs toward reliable professional assistance. The code is available at https://github.com/FDU-INS/INS-ActBench.
: Environmental, Social, and Governance (ESG) evaluation is traditionally treated as a predictive task, where machine learning models estimate scores from financial and contextual features. Such approaches remain fundamentally limited: they provide predictions without structured reasoning, fail to resolve conflicting signals, and cannot support counterfactual decision analysis. This paper proposes a Machine Reasoning (MR) framework that transforms ESG evaluation into a structured decision-making process. The system decomposes ESG evidence into three independent streams: environmental efficiency, financial comparative position, and causal profit-margin effects estimated via DoWhy, and integrates them through five conditional reasoning regimes that resolve conflicts rather than average them. The architecture possesses three properties absent from standard ML pipelines, explanations are produced by the same conditional logic that generates predictions, not inferred post-hoc; hard weight discontinuities at regime boundaries prevent financial strength from compensating for environmental failure; and counterfactual interventions re-run the full reasoning pipeline, capturing non-linear regime shifts that surrogate-model approaches cannot represent. Validated on 11,000 firm-year observations without lagged ESG inputs, the fusion model achieves R²=0.641, a +0.44 R² gain over financial-only baselines with structured decision traces and intervention analysis as additional outputs.
Nizam Tanzina, Kyupil Yeon· International Conference on...· 0 citations
Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matching? The financial domain, demanding numerical precision and multi-step logic over long contexts, is an ideal testbed. Existing benchmarks fail to capture real-world industrial complexity, predominantly relying on multiple-choice questions or single-hop QA over cropped tables while ignoring intricate cross-statement dynamics and temporal de-cumulation. To bridge this gap, we introduce FinIndices, a large-scale benchmark evaluating data-processing fidelity over uncropped financial statements (up to 32K tokens). Utilizing an automated synthesis pipeline with adversarial traps, FinIndices encompasses Single-Index computation and Table-Index tabulation to test complex domain, temporal, and caliber reasoning. Our evaluation reveals two severe LLM vulnerabilities. First, a"Knowledge Bottleneck": despite memorizing formulas during pre-training, models demonstrate fragile pattern matching. Removing explicit formula hints causes performance to collapse (e.g., Gemini-3.1-Pro drops from 70.70% to 38.22% on table tasks), exposing fatal flaws in temporal de-cumulation and stock-flow caliber mismatch. Second, a"Structural Bottleneck": the intense cognitive load of generating multi-metric, multi-period tables actively drains reasoning capacity. Under structural pressure, LLMs that flawlessly execute isolated derivations regress to shallow heuristics, such as fetching incorrect adjacent columns or substituting deep accounting adjustments with lazy literal arithmetic. Finally, Supervised Fine-Tuning (SFT) yields substantial zero-hint gains (+8.54% Single, +3.82% Table), validating that structured logic can be partially restored via data-centric alignment.
In capital-markets workflows the question is rarely whether a large language model can produce a fluent draft, but whether the draft is bankable: defensible in front of a counter-party or a regulator, with the documents in hand. Existing methods address parts of that gap: open-domain QA benchmarks reward surface accuracy, and finance benchmarks (FinanceBench, FinQA, ConvFinQA) advance document-grounded and numerical QA but evaluate at the question-answer layer rather than the workflow outputs practitioners defend. We introduce CM-LRS, a Capital Markets LLM Reliability Score, evaluating outputs at the workflow-output layer across seven dimensions: factual accuracy, evidence traceability, numerical consistency, workflow completeness, source discipline, decision usefulness, and reviewability/auditability. Each is scored 0-5 against a rubric anchored on signals reviewers in regulated settings use; the aggregate is tunable to the workflow. We demonstrate CM-LRS on five workflows (DCM transaction-terms extraction, precedent retrieval, issuer profile synthesis, M&A transaction-comparable reasoning, ECM transaction-terms extraction) over public SEC EDGAR filings, a public UK takeover release, and fictional synthetic supplements, scoring four models against four independent LLM judges spanning three model families. Three findings. First, the frontier closed-source models cluster within 0.22 points on four-judge averaged CM-LRS (Sonnet 4.6 = 4.31, Opus 4.7 = 4.30, GPT-5.5 = 4.09); all four judges place the open-weights baseline (Llama 3.3 70B = 3.15) last. Second, that gap concentrates on retrieval (2.23) and synthesis (2.15), not extraction (0.84). Third, Decision Usefulness shows the widest cross-model dispersion of any dimension (4.0 points on issuer profiling) and top-tier inter-judge agreement (mean r = 0.52). Plausibility is cheap. Bankability is the bar.
It is demonstrated that GRPO with a finance-grounded reward signal can produce substantially more useful business recommendations than commercial LLMs, and that a judge-independent causal audit is a valuable complement to, rather than a confirmation of, LLM-as-a-judge assessment in financial NLP.
Ofir Ben Shoham, Shrutendra Harsola, Vignesh T. Subrahmaniam et al.· 0 citations
Large language models are increasingly used to support financial operations, but their apparent reasoning performance can depend on whether they receive the right evidence. In financial reconciliation, the evidence needed for diagnosis is distributed across invoices, purchase orders, approvals, allocations, payments, ledger entries, and bank activity, linked by transactional relationships rather than textual similarity. End-to-end accuracy can therefore conflate evidence access with reasoning quality. We introduce FinRCA-Bench, a deterministic synthetic benchmark of 2,250 accounts-payable-to-bank reconciliation cases spanning 14 operational tables, including 1,500 injected failures across 15 causal categories and 750 legitimate or hard-negative cases. Root-cause labels and record-level evidence contracts are hidden from the model, allowing retrieval to be evaluated independently of answer correctness. We compare Rules/SQL, classical machine learning, dense semantic retrieval, deterministic relational expansion, and Typed Provenance Graph Retrieval (TPGR), a typed traversal restricted to persisted transaction relationships. Rules/SQL reaches 84.97% held-out exact accuracy and classical ML reaches 95.44%. Holding the reasoning model, prompt, and generation settings fixed while changing only retrieval increases macro required-record recall from 0.83% to 77.70% and exact 16-class accuracy from 2.05% to 72.44%. Structural retrieval failures outnumber reasoning failures with sufficient retrieval by 95 to 15; 254 correct predictions occur despite incomplete retrieval, and strict returned-evidence contract accuracy is only 5.72%. On FinRCA-Bench, retrieval architecture strongly shapes observed AI-system performance, and a correct root-cause label is a weak proxy for an auditable diagnosis.
Prof. S. B. Ghawate· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
