{"total":141,"rows":[{"id":"2407.06567","title":"FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making","created":"2024-07-09","cited_by_count":113,"area":"agents"},{"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":"2503.16858","title":"MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering","created":"2025-03-21","cited_by_count":55,"area":"lr"},{"id":"2406.05688","title":"Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions","created":"2024-06-09","cited_by_count":46,"area":null},{"id":"2408.11878","title":"Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications","created":"2024-08-20","cited_by_count":36,"area":"mllm"},{"id":"2502.08127","title":"Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance","created":"2025-02-12","cited_by_count":35,"area":"lr"},{"id":"2505.24714","title":"FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation","created":"2025-05-30","cited_by_count":30,"area":"lr"},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2505.11065","title":"Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking","created":"2025-05-16","cited_by_count":21,"area":null},{"id":"2509.11575","title":"A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models","created":"2025-09-15","cited_by_count":21,"area":"lr"},{"id":"2410.04526","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","created":"2024-10-06","cited_by_count":20,"area":"lr"},{"id":"2409.19667","title":"Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models","created":"2024-09-29","cited_by_count":17,"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":"2502.15865","title":"Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk","created":"2025-02-21","cited_by_count":13,"area":"agents"},{"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":"2502.05878","title":"Retrieval-augmented Large Language Models for Financial Time Series Forecasting","created":"2025-02-09","cited_by_count":12,"area":"rag"},{"id":"2505.19819","title":"FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets","created":"2025-05-26","cited_by_count":12,"area":null},{"id":"2512.13168","title":"Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2505.22959","title":"LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements","created":"2025-05-29","cited_by_count":9,"area":"lr"},{"id":"2501.06211","title":"FLAME: Financial Large-Language Model Assessment and Metrics Evaluation","created":"2025-01-03","cited_by_count":8,"area":null},{"id":"2409.04475","title":"Revolutionizing Database Q&A with Large Language Models: Comprehensive Benchmark and Evaluation","created":"2024-09-05","cited_by_count":7,"area":null},{"id":"2412.10906","title":"SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation","created":"2024-12-14","cited_by_count":7,"area":null},{"id":"2502.06329","title":"Expect the Unexpected: FailSafe Long Context QA for Finance","created":"2025-02-10","cited_by_count":7,"area":null},{"id":"2603.00025","title":"TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation","created":"2026-02-03","cited_by_count":7,"area":"alignment"},{"id":"2605.19337","title":"Agentic Trading: When LLM Agents Meet Financial Markets","created":"2026-05-19","cited_by_count":7,"area":"agents"},{"id":"2606.03829","title":"BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents","created":"2026-06-02","cited_by_count":7,"area":"agents"},{"id":"2404.07452","title":"RiskLabs: Predicting Financial Risk Using Large Language Model based on Multimodal and Multi-Sources Data","created":"2024-04-11","cited_by_count":6,"area":null},{"id":"2405.14766","title":"Evaluating Large Language Models for Public Health Classification and Extraction Tasks","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2411.07264","title":"Multi-Document Financial Question Answering using LLMs","created":"2024-11-08","cited_by_count":6,"area":null},{"id":"2506.03750","title":"MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"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":"2603.22651","title":"Benchmarking Multi-Agent LLM Architectures for Financial Document Processing: A Comparative Study of Orchestration Patterns, Cost-Accuracy Tradeoffs and Production Scaling Strategies","created":"2026-03-24","cited_by_count":6,"area":"agents"},{"id":"2605.15412","title":"From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery","created":"2026-05-14","cited_by_count":6,"area":null},{"id":"2506.04290","title":"Interpretable LLMs for Credit Risk: A Systematic Review and Taxonomy","created":"2025-06-04","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":"2603.02702","title":"FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing","created":"2026-03-03","cited_by_count":5,"area":null},{"id":"2603.16112","title":"ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning","created":"2026-03-17","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":"2503.18313","title":"Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective","created":"2025-03-24","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":"2601.13082","title":"Adversarial News and Lost Profits: Manipulating Headlines in LLM-Driven Algorithmic Trading","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2603.00285","title":"TraderBench: How Robust Are AI Agents in Adversarial Capital Markets?","created":"2026-02-27","cited_by_count":4,"area":"agents"},{"id":"2603.04403","title":"FinRetrieval: A Benchmark for Financial Data Retrieval by AI Agents","created":"2026-01-02","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":"2604.10015","title":"FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2605.10267","title":"IndustryBench: Probing the Industrial Knowledge Boundaries of LLMs","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2605.14355","title":"Herculean: An Agentic Benchmark for Financial Intelligence","created":"2026-05-14","cited_by_count":4,"area":"agents"},{"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":"2605.22664","title":"MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance","created":"2026-05-21","cited_by_count":4,"area":"agents"},{"id":"2608.11683","title":"FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents","created":"2026-08-12","cited_by_count":4,"area":"agents"},{"id":"2505.13425","title":"Learnware of Language Models: Specialized Small Language Models Can Do Big","created":"2025-05-19","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":"2506.16163","title":"Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behavior","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2507.22758","title":"MASCA: LLM based-Multi Agents System for Credit Assessment","created":"2025-07-30","cited_by_count":3,"area":"agents"},{"id":"2601.15047","title":"Game-Theoretic Lens on LLM-based Multi-Agent Systems","created":"2026-01-21","cited_by_count":3,"area":"lr"},{"id":"2605.16895","title":"The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"id":"2606.06960","title":"FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards","created":"2026-06-05","cited_by_count":3,"area":"agents"},{"id":"2404.09260","title":"JaFIn: Japanese Financial Instruction Dataset","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2406.11328","title":"Are Large Language Models True Healthcare Jacks-of-All-Trades? Benchmarking Across Health Professions Beyond Physician Exams","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2503.20990","title":"FinAudio: A Benchmark for Audio Large Language Models in Financial Applications","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2504.13125","title":"LLMs Meet Finance: Fine-Tuning Foundation Models for the Open FinLLM Leaderboard","created":"2025-04-17","cited_by_count":2,"area":null},{"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":"2507.22936","title":"Evaluating Large Language Models (LLMs) in Financial NLP: A Comparative Study on Financial Report Analysis","created":"2025-07-24","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":"2602.18481","title":"AlphaForgeBench: Benchmarking End-to-End Trading Strategy Design with Large Language Models","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2603.05776","title":"PVminerLLM: Structured Extraction of Patient Voice from Patient-Generated Text using Large Language Models","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2604.02368","title":"Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2607.19409","title":"FORCE-Bench: A Benchmark, Dataset, and Evaluation Harness for Agentic AI in Enterprise Finance","created":"2026-07-11","cited_by_count":2,"area":"agents"},{"id":"2411.09937","title":"Refined and Segmented Price Sentiment Indices from Survey Comments","created":"2024-11-15","cited_by_count":1,"area":null},{"id":"2502.02573","title":"Are Language Models Up to Sequential Optimization Problems? From Evaluation to a Hegelian-Inspired Enhancement","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2502.18471","title":"FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2503.15985","title":"Exploring the Reliability of Self-explanation and its Relationship with Classification in Language Model-driven Financial Analysis","created":"2025-03-20","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":"2505.21807","title":"TabReason: A Reinforcement Learning-Enhanced Reasoning LLM for Explainable Tabular Data Prediction","created":"2025-05-27","cited_by_count":1,"area":"lr"},{"id":"2506.11017","title":"TeleEval-OS: Performance evaluations of large language models for operations scheduling","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2507.08339","title":"What Factors Affect LLMs and RLLMs in Financial Question Answering?","created":"2025-07-11","cited_by_count":1,"area":"lr"},{"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":"2509.24342","title":"Fin-Ally: Pioneering the Development of an Advanced, Commonsense-Embedded Conversational AI for Money Matters","created":"2025-09-29","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":"2510.03349","title":"AgentCaster: Reasoning-Guided Tornado Forecasting","created":"2025-10-02","cited_by_count":1,"area":"lr"},{"id":"2511.04705","title":"POLIS-Bench: Towards Multi-Dimensional Evaluation of LLMs for Bilingual Policy Tasks in Governmental Scenarios","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2512.08270","title":"Reasoning Models Ace the CFA Exams","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2512.12264","title":"Market-Bench: Evaluating Large Language Models on Introductory Quantitative Trading and Market Dynamics","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2601.06088","title":"PriceSeer: Evaluating Large Language Models in Real-Time Stock Prediction","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2601.09151","title":"Interpretable Probability Estimation with LLMs via Shapley Reconstruction","created":"2026-01-14","cited_by_count":1,"area":"lr"},{"id":"2601.11863","title":"Utilizing Metadata for Better Retrieval-Augmented Generation","created":"2026-01-17","cited_by_count":1,"area":"rag"},{"id":"2603.08704","title":"Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines","created":"2026-03-09","cited_by_count":1,"area":"lr"},{"id":"2603.10002","title":"SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.16434","title":"From Natural Language to Executable Option Strategies via Large Language Models","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2603.20252","title":"FinReflectKG -- HalluBench: GraphRAG Hallucination Benchmark for Financial Question Answering Systems","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2603.23646","title":"Swiss-Bench SBP-002: A Frontier Model Comparison on Swiss Legal and Regulatory Tasks","created":"2026-03-24","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":"2606.03918","title":"Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning","created":"2026-06-02","cited_by_count":1,"area":null},{"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":"2606.31522","title":"FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2607.01740","title":"Meta-Benchmarks for Financial-Services LLM Evaluation","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.20491","title":"DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2608.19558","title":"Reliable Financial Named Entity Recognition Under Domain Shift: Confidence Estimation and Selective Prediction","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2608.21036","title":"Evaluating Large Language Model Performance on International Maritime Dangerous Goods Code Compliance","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2504.18024","title":"SMARTFinRAG: Interactive Modularized Financial RAG Benchmark","created":"2025-04-25","cited_by_count":0,"area":"rag"}],"next_cursor":"100"}