{"total":15,"rows":[{"id":"2601.06992","title":"FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering","created":"2026-01-11","cited_by_count":16,"area":null},{"id":"2506.14028","title":"MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application","created":"2025-06-16","cited_by_count":14,"area":null},{"id":"2602.05150","title":"GreekMMLU: A Native-Sourced Multitask Benchmark for Evaluating Language Models in Greek","created":"2026-02-05","cited_by_count":6,"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":"2505.20650","title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2509.04455","title":"INSEva: A Comprehensive Chinese Benchmark for Large Language Models in Insurance","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2602.10886","title":"The CLEF-2026 FinMMEval Lab: Multilingual and Multimodal Evaluation of Financial AI Systems","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2602.16811","title":"Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2608.12342","title":"Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2506.05700","title":"RKEFino1: A Regulation Knowledge-Enhanced Large Language Model","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2604.01957","title":"Diagnosing Translated Benchmarks: An Automated Quality Assurance Study of the EU20 Benchmark Suite","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.08948","title":"TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2609.34800","title":"Pass or Fail? Evaluating LLMs on Two Greek Examination Benchmarks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.14101","title":"Fin_Agent at FinEval 2026: Task-Aware Methods for Multilingual Financial NLP","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.19432","title":"Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extraction","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}