{"total":120,"rows":[{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205,"area":null},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183,"area":null},{"id":"2402.12659","title":"FinBen: A Holistic Financial Benchmark for Large Language Models","created":"2024-02-20","cited_by_count":141,"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":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2405.09980","title":"FinTextQA: A Dataset for Long-form Financial Question Answering","created":"2024-05-16","cited_by_count":54,"area":null},{"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":"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":"2501.04961","title":"Demystifying Domain-adaptive Post-training for Financial LLMs","created":"2025-01-09","cited_by_count":24,"area":null},{"id":"2405.10542","title":"Benchmarking Large Language Models on CFLUE -- A Chinese Financial Language Understanding Evaluation Dataset","created":"2024-05-17","cited_by_count":23,"area":null},{"id":"2411.03538","title":"Long Context RAG Performance of Large Language Models","created":"2024-11-05","cited_by_count":23,"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":"2409.13989","title":"ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models","created":"2024-09-21","cited_by_count":18,"area":null},{"id":"2502.10990","title":"FinMTEB: Finance Massive Text Embedding Benchmark","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2502.18772","title":"Plutus: Benchmarking Large Language Models in Low-Resource Greek Finance","created":"2025-02-26","cited_by_count":18,"area":null},{"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":"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":"2502.11075","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models","created":"2025-02-16","cited_by_count":14,"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":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"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":"2411.07142","title":"Greenback Bears and Fiscal Hawks: Finance is a Jungle and Text Embeddings Must Adapt","created":"2024-11-11","cited_by_count":12,"area":null},{"id":"2503.14190","title":"Inferring Events from Time Series using Language Models","created":"2025-03-18","cited_by_count":10,"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":"2602.07096","title":"RealFin: How Well Do LLMs Reason About Finance When Users Leave Things Unsaid?","created":"2026-02-06","cited_by_count":9,"area":null},{"id":"2411.02476","title":"A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification","created":"2024-11-04","cited_by_count":8,"area":null},{"id":"2411.11767","title":"Drowning in Documents: Consequences of Scaling Reranker Inference","created":"2024-11-18","cited_by_count":8,"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":"2506.01646","title":"ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2506.15594","title":"WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts","created":"2025-06-18","cited_by_count":8,"area":null},{"id":"2510.22548","title":"LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?","created":"2025-10-26","cited_by_count":8,"area":null},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2403.06249","title":"No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks","created":"2024-03-10","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":"2504.04596","title":"SECQUE: A Benchmark for Evaluating Real-World Financial Analysis Capabilities","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2410.15653","title":"Opportunities and Challenges of Generative-AI in Finance","created":"2024-10-21","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":"2504.05324","title":"Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis","created":"2025-02-28","cited_by_count":5,"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":"2503.22693","title":"Bridging Language Models and Financial Analysis","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2506.15846","title":"Finance Language Model Evaluation (FLaME)","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","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":"2604.15151","title":"QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies","created":"2026-04-16","cited_by_count":4,"area":null},{"id":"2604.23588","title":"FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification","created":"2026-04-26","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":"2504.06293","title":"Generative AI Enhanced Financial Risk Management Information Retrieval","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2604.05912","title":"FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks","created":"2026-04-07","cited_by_count":3,"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":"2606.15949","title":"FinBalance: A Multi-Document Accounting Reconciliation Benchmark","created":"2026-06-14","cited_by_count":3,"area":null},{"id":"2608.06144","title":"FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows","created":"2026-08-06","cited_by_count":3,"area":null},{"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":"2405.10212","title":"CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations","created":"2024-05-16","cited_by_count":2,"area":null},{"id":"2505.16661","title":"A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2506.02510","title":"M$^3$FinMeeting: A Multilingual, Multi-Sector, and Multi-Task Financial Meeting Understanding Evaluation Dataset","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.02596","title":"EssayBench: Evaluating Large Language Models in Multi-Genre Chinese Essay Writing","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2508.07353","title":"Benchmarking for Domain-Specific LLMs: A Case Study on Academia and Beyond","created":"2025-08-10","cited_by_count":2,"area":null},{"id":"2509.09544","title":"MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022-2025)","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2511.19671","title":"FISCAL: Financial Synthetic Claim-document Augmented Learning for Efficient Fact-Checking","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2601.02285","title":"pdfQA: Diverse, Challenging, and Realistic Question Answering over PDFs","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2601.21969","title":"Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.17687","title":"IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2604.22239","title":"Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2604.22294","title":"SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2607.11192","title":"GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents","created":"2026-07-13","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":"2411.03300","title":"VERITAS: A Unified Approach to Reliability Evaluation","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2507.06795","title":"ixi-GEN: Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining","created":"2025-07-09","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":"2603.20316","title":"Bypassing Document Ingestion: An MCP Approach to Financial Q&A","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2603.23562","title":"Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.19765","title":"Do Hallucination Neurons Generalize? Evidence from Cross-Domain Transfer in LLMs","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2605.26937","title":"Beyond Questions: Evaluating the Stated Knowledge of LLMs","created":"2026-05-26","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":"2606.04646","title":"QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples","created":"2026-06-03","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":"2607.24273","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":"2608.01204","title":"ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2608.07400","title":"FinRank: An Evidence-Grounded Benchmark for Financial Question Answering and Retrieval over SEC Filings","created":"2026-08-07","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":"2609.10494","title":"IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2409.13749","title":"KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2410.02024","title":"FLAG: Financial Long Document Classification via AMR-based GNN","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2412.06693","title":"OmniEvalKit: A Modular, Lightweight Toolbox for Evaluating Large Language Model and its Omni-Extensions","created":"2024-12-09","cited_by_count":0,"area":null},{"id":"2412.09884","title":"Benchmarking Table Comprehension In The Wild","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2504.13216","title":"KFinEval-Pilot: A Comprehensive Benchmark Suite for Korean Financial Language Understanding","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2505.22752","title":"Climate Finance Bench","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2512.08088","title":"Adaptation of Embedding Models to Financial Filings via LLM Distillation","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.06747","title":"FinForge: Semi-Synthetic Financial Benchmark Generation","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2604.16826","title":"Crowded in B-Space: Calibrating Shared Directions for LoRA Merging","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2604.19298","title":"IndiaFinBench: An Evaluation Benchmark for Large Language Model Performance on Indian Financial Regulatory Text","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.05482","title":"FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.18824","title":"Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models","created":"2026-05-12","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":"2607.01245","title":"Office Comprehension Benchmark","created":"2026-05-29","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":"2607.19856","title":"Overview of FinMMEval 2026 Task 1: Multilingual Financial Multiple-Choice Question Answering","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.19867","title":"Overview of FinMMEval 2026 Task 2: Multilingual Financial Short-Answer Question Answering","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.21340","title":"Capital Markets LLM Reliability Score (CM-LRS): From Plausible to Bankable","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.25135","title":"ScalableRAG: High-Quality RAG at Zero Ingestion Cost","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":"100"}