# FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Review

arXiv: https://arxiv.org/abs/2608.25325 · HTML: https://mlsanity.com/paper/2608.25325/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 38 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 30 of 33)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering](https://mlsanity.com/paper/2210.03849/) (2022)
- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [FinBen: A Holistic Financial Benchmark for Large Language Models](https://mlsanity.com/paper/2402.12659/) (2024)
- [WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain](https://mlsanity.com/paper/2211.00083/) (2022)
- [LawBench: Benchmarking Legal Knowledge of Large Language Models](https://mlsanity.com/paper/2309.16289/) (2023)
- [Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information](https://mlsanity.com/paper/1805.04655/) (2018)
- [Selectively Answering Ambiguous Questions](https://mlsanity.com/paper/2305.14613/) (2023)
- [Finance Agent Benchmark: Benchmarking LLMs on Real-world Financial Research Tasks](https://mlsanity.com/paper/2508.00828/) (2025)
- [QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?](https://mlsanity.com/paper/2503.22674/) (2025)
- [CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models](https://mlsanity.com/paper/2405.12063/) (2024)
- [FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2308.09975/) (2023)
- [BizBench: A Quantitative Reasoning Benchmark for Business and Finance](https://mlsanity.com/paper/2311.06602/) (2023)
- [FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging](https://mlsanity.com/paper/2506.05828/) (2025)
- [From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?](https://mlsanity.com/paper/2506.08295/) (2025)
- [DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models](https://mlsanity.com/paper/2505.14107/) (2025)
- [When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification](https://mlsanity.com/paper/2602.11199/) (2026)
- [CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models](https://mlsanity.com/paper/2407.02301/) (2024)
- [RealFin: How Well Do LLMs Reason About Finance When Users Leave Things Unsaid?](https://mlsanity.com/paper/2602.07096/) (2026)
- [I Could've Asked That: Reformulating Unanswerable Questions](https://mlsanity.com/paper/2407.17469/) (2024)
- [Beyond Knowledge to Agency: Evaluating Expertise, Autonomy, and Integrity in Finance with CNFinBench](https://mlsanity.com/paper/2512.09506/) (2025)
- [Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs](https://mlsanity.com/paper/2510.25441/) (2025)

## Abstract (arXiv)

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.