{"total":60,"rows":[{"id":"2406.10149","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","created":"2024-06-14","cited_by_count":215,"area":"lr"},{"id":"2404.11912","title":"TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding","created":"2024-04-18","cited_by_count":102,"area":"inference"},{"id":"2411.06176","title":"M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework","created":"2024-11-09","cited_by_count":36,"area":null},{"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":"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":"2407.00402","title":"Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP","created":"2024-06-29","cited_by_count":27,"area":null},{"id":"2502.13668","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","created":"2025-02-19","cited_by_count":22,"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":"2502.16111","title":"PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving","created":"2025-02-22","cited_by_count":15,"area":"lr"},{"id":"2410.04698","title":"MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs","created":"2024-10-07","cited_by_count":13,"area":"lr"},{"id":"2502.12462","title":"Emulating Retrieval Augmented Generation via Prompt Engineering for Enhanced Long Context Comprehension in LLMs","created":"2025-02-18","cited_by_count":9,"area":"lr"},{"id":"2505.15865","title":"How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads","created":"2025-05-21","cited_by_count":9,"area":"mllm"},{"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":"2410.12583","title":"STRUX: An LLM for Decision-Making with Structured Explanations","created":"2024-10-16","cited_by_count":7,"area":null},{"id":"2511.07585","title":"LLM Output Drift: Cross-Provider Validation & Mitigation for Financial Workflows","created":"2025-11-10","cited_by_count":7,"area":null},{"id":"2606.03829","title":"BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents","created":"2026-06-02","cited_by_count":7,"area":"agents"},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"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":"2509.12042","title":"FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval","created":"2025-09-15","cited_by_count":5,"area":"rag"},{"id":"2410.01772","title":"DeFine: Decision-Making with Analogical Reasoning over Factor Profiles","created":"2024-10-02","cited_by_count":4,"area":"lr"},{"id":"2412.21006","title":"Verbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled Criteria","created":"2024-12-30","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":"2510.24402","title":"Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering","created":"2025-10-28","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":"2604.23588","title":"FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification","created":"2026-04-26","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":"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":"2503.16575","title":"Extract, Match, and Score: An Evaluation Paradigm for Long Question-context-answer Triplets in Financial Analysis","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2504.07274","title":"Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunities","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2506.12958","title":"Domain Specific Benchmarks for Evaluating Multimodal Large Language Models","created":"2025-06-15","cited_by_count":3,"area":"mllm"},{"id":"2510.10828","title":"VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering","created":"2025-10-12","cited_by_count":3,"area":"rag"},{"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":"2606.15949","title":"FinBalance: A Multi-Document Accounting Reconciliation Benchmark","created":"2026-06-14","cited_by_count":3,"area":null},{"id":"2604.04347","title":"RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2406.05369","title":"Venn Diagram Prompting : Accelerating Comprehension with Scaffolding Effect","created":"2024-06-08","cited_by_count":1,"area":null},{"id":"2510.02906","title":"FinReflectKG -- MultiHop: Financial QA Benchmark for Reasoning with Knowledge Graph Evidence","created":"2025-10-03","cited_by_count":1,"area":"lr"},{"id":"2604.07981","title":"A Decomposition Perspective to Long-context Reasoning for LLMs","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2606.13100","title":"LEDGER: A Long-Context Benchmark of Corporate Annual Reports for Grounded Financial Retrieval and Extraction","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.18831","title":"Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning","created":"2026-06-17","cited_by_count":1,"area":"lr"},{"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":"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":"2608.00764","title":"FinDeepIndicator: Benchmarking Deep Research Agents in End-to-End Financial Indicator Construction","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"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":"2509.23259","title":"Fin-ExBERT: User Intent based Text Extraction in Financial Context using Graph-Augmented BERT and trainable Plugin","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2511.05000","title":"Query Generation Pipeline with Enhanced Answerability Assessment for Financial Information Retrieval","created":"2025-11-07","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":"2512.08965","title":"Financial Instruction Following Evaluation (FIFE)","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.22162","title":"UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos","created":"2026-01-09","cited_by_count":0,"area":"lr"},{"id":"2603.05529","title":"NGDBench: Towards Neural Graph Data Management","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2604.05114","title":"$\\pi^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"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":"2606.11537","title":"MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.19416","title":"MortarBench: Evaluating Mortgage Loan Origination Agents","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2607.18102","title":"FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering","created":"2026-07-20","cited_by_count":0,"area":"rag"},{"id":"2608.04374","title":"FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.27790","title":"Credo: Reusable Declarative Primitives for Agentic Workflows","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.03654","title":"Enhancing Financial Question Answering: A Novel Benchmark Dataset of Banks' financial statements","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.24002","title":"FinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.33143","title":"CAME: Company-Aware Evidence-Memory Experts for Interpretable Quarter-Ahead Revenue Forecasting","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.19432","title":"Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extraction","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}