{"total":19,"rows":[{"id":"2511.11562","title":"PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning","created":"2025-11-14","cited_by_count":32,"area":null},{"id":"2602.14233","title":"Evaluating LLMs in Finance Requires Explicit Bias Consideration","created":"2026-02-15","cited_by_count":11,"area":null},{"id":"2510.15232","title":"FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2602.07294","title":"Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filings","created":"2026-02-07","cited_by_count":8,"area":null},{"id":"2603.07223","title":"Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2605.15482","title":"FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.27887","title":"PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2601.15714","title":"Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2604.05387","title":"Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2607.24273","title":"INS-ActBench: A Comprehensive Benchmark for Assessing Professional Actuarial Capability of Large Language Models","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2601.06401","title":"BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2604.08454","title":"Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.29586","title":"FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.31064","title":"Fighting Numerical Hallucinations via Data-centric Compilation for Online Financial QA","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.11537","title":"MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.25325","title":"FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Review","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.28155","title":"FinExam-10K: When Retrieval Helps Financial Reasoning?","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.01386","title":"When Tokenization is Secretly Output Supervision","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.03564","title":"Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}