{"total":30,"rows":[{"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":"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":"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":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"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":"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":"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":"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":"2406.05369","title":"Venn Diagram Prompting : Accelerating Comprehension with Scaffolding Effect","created":"2024-06-08","cited_by_count":1,"area":null},{"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":"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":"2608.07400","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":"2603.05529","title":"NGDBench: Towards Neural Graph Data Management","created":"2026-02-27","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":"2606.11537","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":"2608.04374","title":"FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation","created":"2026-08-05","cited_by_count":0,"area":null},{"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":"2609.33143","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}