{"total":270,"rows":[{"id":"2501.13956","title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","created":"2025-01-20","cited_by_count":400,"area":"agents"},{"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":"2408.04948","title":"HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction","created":"2024-08-09","cited_by_count":93,"area":"rag"},{"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":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"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":"2407.08488","title":"Lynx: An Open Source Hallucination Evaluation Model","created":"2024-07-11","cited_by_count":57,"area":"rag"},{"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":"2405.09980","title":"FinTextQA: A Dataset for Long-form Financial Question Answering","created":"2024-05-16","cited_by_count":54,"area":null},{"id":"2402.05131","title":"Financial Report Chunking for Effective Retrieval Augmented Generation","created":"2024-02-05","cited_by_count":46,"area":"rag"},{"id":"2603.08655","title":"OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning","created":"2026-03-09","cited_by_count":39,"area":"lr"},{"id":"2505.16997","title":"X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs","created":"2025-05-22","cited_by_count":38,"area":"agents"},{"id":"2502.12342","title":"REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark","created":"2025-02-17","cited_by_count":35,"area":"rag"},{"id":"2402.10986","title":"FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models","created":"2024-02-16","cited_by_count":32,"area":"mllm"},{"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":"2505.24714","title":"FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation","created":"2025-05-30","cited_by_count":30,"area":"lr"},{"id":"2412.13018","title":"OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain","created":"2024-12-17","cited_by_count":29,"area":"rag"},{"id":"2508.14052","title":"FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering","created":"2025-08-07","cited_by_count":29,"area":"agents"},{"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":"2506.14852","title":"Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents","created":"2025-06-17","cited_by_count":27,"area":"agents"},{"id":"2412.02592","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","created":"2024-12-03","cited_by_count":26,"area":"rag"},{"id":"2411.01106","title":"SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding","created":"2024-11-02","cited_by_count":25,"area":"mllm"},{"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":"2410.04526","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","created":"2024-10-06","cited_by_count":20,"area":"lr"},{"id":"2502.15964","title":"Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models","created":"2025-02-21","cited_by_count":20,"area":"lr"},{"id":"2409.12558","title":"RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues","created":"2024-09-19","cited_by_count":19,"area":"rag"},{"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":"2504.15800","title":"FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation","created":"2025-04-22","cited_by_count":17,"area":"rag"},{"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":"2508.07493","title":"VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding","created":"2025-08-10","cited_by_count":14,"area":"rag"},{"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":"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":"2404.11792","title":"Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study","created":"2024-04-17","cited_by_count":11,"area":"lr"},{"id":"2411.13768","title":"Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture","created":"2024-11-21","cited_by_count":11,"area":"agents"},{"id":"2605.28359","title":"From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock Markets","created":"2026-05-27","cited_by_count":11,"area":"agents"},{"id":"2503.14190","title":"Inferring Events from Time Series using Language Models","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2503.18825","title":"EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents","created":"2025-03-24","cited_by_count":10,"area":"agents"},{"id":"2512.13168","title":"Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2602.23368","title":"Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use","created":"2025-12-19","cited_by_count":10,"area":"rag"},{"id":"2603.08262","title":"FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use","created":"2026-03-09","cited_by_count":10,"area":"agents"},{"id":"2503.15191","title":"Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems","created":"2025-03-19","cited_by_count":9,"area":"rag"},{"id":"2506.08136","title":"EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"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":"2503.05185","title":"Towards Temporal-Aware Multi-Modal Retrieval Augmented Generation in Finance","created":"2025-03-07","cited_by_count":8,"area":"rag"},{"id":"2504.19101","title":"Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation","created":"2025-04-27","cited_by_count":8,"area":"rag"},{"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":"2507.21134","title":"TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law","created":"2025-07-22","cited_by_count":8,"area":"safety"},{"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":"2512.21720","title":"An Information Theoretic Perspective on Agentic System Design","created":"2025-12-25","cited_by_count":8,"area":"agents"},{"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":"2411.03314","title":"MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning","created":"2024-11-05","cited_by_count":7,"area":"lr"},{"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":"2602.05014","title":"DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search","created":"2026-02-04","cited_by_count":7,"area":"lr"},{"id":"2605.05971","title":"Training Transformers for KV Cache Compressibility","created":"2026-05-07","cited_by_count":7,"area":"inference"},{"id":"2606.03829","title":"BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents","created":"2026-06-02","cited_by_count":7,"area":"agents"},{"id":"2402.16211","title":"HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMs","created":"2024-02-25","cited_by_count":6,"area":"alignment"},{"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":"2507.02954","title":"Advanced Financial Reasoning at Scale: A Comprehensive Evaluation of Large Language Models on CFA Level III","created":"2025-06-29","cited_by_count":6,"area":"lr"},{"id":"2511.07322","title":"FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation","created":"2025-11-10","cited_by_count":6,"area":"agents"},{"id":"2503.16856","title":"MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers","created":"2025-03-21","cited_by_count":5,"area":"lr"},{"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":"2505.20266","title":"syftr: Pareto-Optimal Generative AI","created":"2025-05-26","cited_by_count":5,"area":"rag"},{"id":"2505.20368","title":"Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documents","created":"2025-05-26","cited_by_count":5,"area":"rag"},{"id":"2603.19225","title":"FinTradeBench: A Financial Reasoning Benchmark for LLMs","created":"2026-03-19","cited_by_count":5,"area":"lr"},{"id":"2608.29856","title":"GenRubric: Self-Evolving Rubric Generation for Scalable LLM Evaluation","created":"2026-08-30","cited_by_count":5,"area":"synth"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"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":"2506.08276","title":"LEANN: A Low-Storage Vector Index","created":"2025-06-09","cited_by_count":4,"area":"rag"},{"id":"2506.15846","title":"Finance Language Model Evaluation (FLaME)","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2507.18932","title":"MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks","created":"2025-07-25","cited_by_count":4,"area":"lr"},{"id":"2509.16369","title":"Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction","created":"2025-09-19","cited_by_count":4,"area":"agents"},{"id":"2510.05825","title":"Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling","created":"2025-10-07","cited_by_count":4,"area":"lr"},{"id":"2510.24402","title":"Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering","created":"2025-10-28","cited_by_count":4,"area":"rag"},{"id":"2512.14744","title":"VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation","created":"2025-12-12","cited_by_count":4,"area":"rag"},{"id":"2601.05039","title":"FinDeepForecast: A Live Multi-Agent System for Benchmarking Deep Research Agents in Financial Forecasting","created":"2026-01-08","cited_by_count":4,"area":"agents"},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2602.10271","title":"MLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation","created":"2026-02-10","cited_by_count":4,"area":"rag"},{"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":"2604.10015","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":"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}],"next_cursor":"100"}