{"total":88,"rows":[{"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":"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":"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":"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":"2407.02301","title":"CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models","created":"2024-07-02","cited_by_count":12,"area":null},{"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":"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":"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":"2506.08762","title":"EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"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":"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":"2603.04403","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":"2605.10267","title":"IndustryBench: Probing the Industrial Knowledge Boundaries of LLMs","created":"2026-05-11","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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"2506.21031","title":"Large Language Models Acing Chartered Accountancy","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2508.16243","title":"TULIP: Adapting Open-Source Large Language Models for Underrepresented Languages and Specialized Financial Tasks","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2508.18636","title":"LaQual: An Automated Framework for LLM App Quality Evaluation","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2509.26331","title":"AI Playing Business Games: Benchmarking Large Language Models on Managerial Decision-Making in Dynamic Simulations","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2511.11315","title":"LAET: A Layer-wise Adaptive Ensemble Tuning Framework for Pretrained Language Models","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2512.14717","title":"Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox","created":"2025-12-09","cited_by_count":0,"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":"2601.09729","title":"Enhancing Business Analytics through Hybrid Summarization of Financial Reports","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2605.14744","title":"Mechanical Enforcement for LLM Governance:Evidence of Governance-Task Decoupling in Financial Decision Systems","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.26074","title":"StakeBench: Evaluating Language Understanding Grounded in Market Commitment","created":"2026-05-25","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":"2606.11166","title":"Flaws in the LLM Automation Narrative","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.15414","title":"AI Trading: Evaluating Large Language Models for Technical Market Analysis","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.28840","title":"Benchmarks Are Not Validation: A System-Level View of Financial LLM Applications","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.17223","title":"Temporal Leakage in Financial News NLP: A Multi-Architecture Audit with a Regime-Specific M&A Signal","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.20116","title":"When Text and Numbers Disagree: Evidence Arbitration in Large Language Models","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.23308","title":"FIDES: A Concordance Protocol for LLM-Generated Trading Strategies","created":"2026-08-24","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":"2609.11656","title":"Learnware and AI Model Management System","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.33521","title":"LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34510","title":"Can AI Make Money in Crypto? Measuring the Gap from Backtests to Real Markets","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.06947","title":"FactorBench: A Portfolio-Aware Benchmark for Automated Factor Mining","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}