{"total":52,"rows":[{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"id":"2406.11903","title":"A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges","created":"2024-06-15","cited_by_count":90,"area":null},{"id":"2503.16252","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","created":"2025-03-20","cited_by_count":83,"area":"lr"},{"id":"2510.02209","title":"StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?","created":"2025-10-02","cited_by_count":44,"area":"agents"},{"id":"2505.19457","title":"BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs","created":"2025-05-26","cited_by_count":22,"area":null},{"id":"2410.01109","title":"Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance -- A Case Study in Finance","created":"2024-10-01","cited_by_count":15,"area":null},{"id":"2511.03628","title":"LiveTradeBench: Seeking Real-World Alpha with Large Language Models","created":"2025-11-05","cited_by_count":13,"area":"lr"},{"id":"2404.00699","title":"A Comprehensive Survey of Contamination Detection Methods in Large Language Models","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2407.02301","title":"CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models","created":"2024-07-02","cited_by_count":12,"area":null},{"id":"2409.18511","title":"Do We Need Domain-Specific Embedding Models? An Empirical Investigation","created":"2024-09-27","cited_by_count":12,"area":null},{"id":"2508.15861","title":"XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning","created":"2025-08-20","cited_by_count":12,"area":"lr"},{"id":"2309.10654","title":"CFGPT: Chinese Financial Assistant with Large Language Model","created":"2023-09-19","cited_by_count":11,"area":null},{"id":"2407.01896","title":"LogEval: A Comprehensive Benchmark Suite for Large Language Models In Log Analysis","created":"2024-07-02","cited_by_count":11,"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":"2408.10947","title":"Dr.Academy: A Benchmark for Evaluating Questioning Capability in Education for Large Language Models","created":"2024-08-20","cited_by_count":6,"area":null},{"id":"2506.08762","title":"EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2507.16802","title":"Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning","created":"2025-07-22","cited_by_count":6,"area":"lr"},{"id":"2509.18776","title":"AECBench: A Hierarchical Benchmark for Knowledge Evaluation of Large Language Models in the AEC Field","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2310.07637","title":"OpsEval: A Comprehensive IT Operations Benchmark Suite for Large Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2506.20274","title":"Enterprise Large Language Model Evaluation Benchmark","created":"2025-06-25","cited_by_count":5,"area":null},{"id":"2507.10448","title":"FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios","created":"2025-07-05","cited_by_count":5,"area":"agents"},{"id":"2602.22273","title":"FIRE: A Comprehensive Benchmark for Financial Intelligence and Reasoning Evaluation","created":"2026-02-25","cited_by_count":5,"area":"lr"},{"id":"2411.06272","title":"Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models","created":"2024-11-09","cited_by_count":4,"area":null},{"id":"2507.18577","title":"Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challenges","created":"2025-07-07","cited_by_count":4,"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":"2407.00365","title":"Financial Knowledge Large Language Model","created":"2024-06-29","cited_by_count":3,"area":null},{"id":"2505.24826","title":"LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal Text","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2509.17628","title":"MSCoRe: A Benchmark for Multi-Stage Collaborative Reasoning in LLM Agents","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2402.07234","title":"CPSDBench: A Large Language Model Evaluation Benchmark and Baseline for Chinese Public Security Domain","created":"2024-02-11","cited_by_count":2,"area":null},{"id":"2501.12399","title":"FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools","created":"2025-01-08","cited_by_count":2,"area":"agents"},{"id":"2506.13066","title":"FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design","created":"2025-06-16","cited_by_count":2,"area":"lr"},{"id":"2506.21591","title":"FinEval-KR: A Financial Domain Evaluation Framework for Large Language Models' Knowledge and Reasoning","created":"2025-06-18","cited_by_count":2,"area":"lr"},{"id":"2509.23488","title":"Mapping Overlaps in Benchmarks through Perplexity in the Wild","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2402.15755","title":"Dental Severity Assessment through Few-shot Learning and SBERT Fine-tuning","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2405.00566","title":"NumLLM: Numeric-Sensitive Large Language Model for Chinese Finance","created":"2024-05-01","cited_by_count":1,"area":null},{"id":"2410.15005","title":"CAP: Data Contamination Detection via Consistency Amplification","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2504.16116","title":"DMind Benchmark: Toward a Holistic Assessment of LLM Capabilities across the Web3 Domain","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.00156","title":"AuditAgent: Expert-Guided Multi-Agent Reasoning for Cross-Document Fraudulent Evidence Discovery","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2605.13779","title":"MinT: Managed Infrastructure for Training and Serving Millions of LLMs","created":"2026-05-13","cited_by_count":1,"area":"moe"},{"id":"2606.19887","title":"FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming","created":"2026-06-18","cited_by_count":1,"area":"safety"},{"id":"2506.07315","title":"Towards Competent AI for Fundamental Analysis in Finance: A Benchmark Dataset and Evaluation","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2511.09754","title":"History Rhymes: Macro-Contextual Retrieval for Robust Financial Forecasting","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2512.24314","title":"QianfanHuijin Technical Report: A Novel Multi-Stage Training Paradigm for Finance Industrial LLMs","created":"2025-12-30","cited_by_count":0,"area":"agents"},{"id":"2602.10819","title":"RePO: Bridging On-Policy Learning and Off-Policy Knowledge through Rephrasing Policy Optimization","created":"2026-02-11","cited_by_count":0,"area":"alignment"},{"id":"2603.14463","title":"An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2605.24414","title":"JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2605.28032","title":"PetroBench: A Benchmark for Large Language Models in Petroleum Engineering","created":"2026-05-27","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":"2609.01045","title":"AgentFactory: Towards Automated Agentic System Design and Optimization","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.25192","title":"FinFIRST: Benchmarking Search Agents for Financial Information Retrieval, Sourcing and Traceability","created":"2026-09-21","cited_by_count":0,"area":"agents"}],"next_cursor":null}