{"total":313,"rows":[{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"area":null},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688,"area":null},{"id":"2311.11944","title":"FinanceBench: A New Benchmark for Financial Question Answering","created":"2023-11-20","cited_by_count":270,"area":null},{"id":"2306.06031","title":"FinGPT: Open-Source Financial Large Language Models","created":"2023-06-09","cited_by_count":253,"area":null},{"id":"2306.05443","title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","created":"2023-06-08","cited_by_count":222,"area":null},{"id":"2305.12524","title":"TheoremQA: A Theorem-driven Question Answering dataset","created":"2023-05-21","cited_by_count":192,"area":null},{"id":"2406.11704","title":"Nemotron-4 340B Technical Report","created":"2024-06-17","cited_by_count":144,"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":"2408.09174","title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","created":"2024-08-17","cited_by_count":128,"area":null},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121,"area":null},{"id":"2401.11641","title":"Revolutionizing Finance with LLMs: An Overview of Applications and Insights","created":"2024-01-22","cited_by_count":90,"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":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","cited_by_count":82,"area":null},{"id":"2309.13064","title":"InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning","created":"2023-09-15","cited_by_count":82,"area":null},{"id":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81,"area":null},{"id":"2402.02315","title":"A Survey of Large Language Models in Finance (FinLLMs)","created":"2024-02-04","cited_by_count":79,"area":null},{"id":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66,"area":null},{"id":"2305.05862","title":"Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks","created":"2023-05-10","cited_by_count":59,"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":"2308.09975","title":"FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models","created":"2023-08-19","cited_by_count":52,"area":null},{"id":"2407.12994","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","created":"2024-07-17","cited_by_count":47,"area":null},{"id":"2210.08817","title":"PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance","created":"2022-10-17","cited_by_count":45,"area":null},{"id":"2201.09745","title":"Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks","created":"2022-01-24","cited_by_count":42,"area":null},{"id":"2411.03766","title":"Number Cookbook: Number Understanding of Language Models and How to Improve It","created":"2024-11-06","cited_by_count":42,"area":null},{"id":"2207.05270","title":"A Survey on Table Question Answering: Recent Advances","created":"2022-07-12","cited_by_count":41,"area":null},{"id":"2305.11541","title":"Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering","created":"2023-05-19","cited_by_count":41,"area":null},{"id":"2307.08153","title":"Analyzing Dataset Annotation Quality Management in the Wild","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2506.12103","title":"The Amazon Nova Family of Models: Technical Report and Model Card","created":"2025-03-17","cited_by_count":41,"area":null},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39,"area":null},{"id":"2505.19797","title":"The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants","created":"2025-05-26","cited_by_count":38,"area":null},{"id":"2601.07206","title":"LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing","created":"2026-01-12","cited_by_count":38,"area":null},{"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":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2310.05155","title":"Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model","created":"2023-10-08","cited_by_count":29,"area":null},{"id":"2402.16671","title":"StructLM: Towards Building Generalist Models for Structured Knowledge Grounding","created":"2024-02-26","cited_by_count":29,"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":"2311.08002","title":"TempTabQA: Temporal Question Answering for Semi-Structured Tables","created":"2023-11-14","cited_by_count":27,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"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":"2502.19400","title":"TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding","created":"2025-02-26","cited_by_count":24,"area":null},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2305.06897","title":"AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages","created":"2023-05-11","cited_by_count":23,"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":"2502.13668","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","created":"2025-02-19","cited_by_count":22,"area":null},{"id":"2210.09162","title":"Table-To-Text generation and pre-training with TabT5","created":"2022-10-17","cited_by_count":20,"area":null},{"id":"2510.19178","title":"Imbalanced Gradients in RL Post-Training of Multi-Task LLMs","created":"2025-10-22","cited_by_count":20,"area":null},{"id":"2109.07323","title":"FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining","created":"2021-09-15","cited_by_count":19,"area":null},{"id":"2411.05764","title":"FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents","created":"2024-11-08","cited_by_count":19,"area":null},{"id":"2501.19378","title":"TableMaster: A Recipe to Advance Table Understanding with Language Models","created":"2025-01-31","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":"2209.07692","title":"Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder","created":"2022-09-16","cited_by_count":17,"area":null},{"id":"2305.11725","title":"S$^3$HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering","created":"2023-05-19","cited_by_count":17,"area":null},{"id":"2406.14394","title":"SEC-QA: A Systematic Evaluation Corpus for Financial QA","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2411.19504","title":"TQA-Bench: Evaluating LLMs for Multi-Table Question Answering","created":"2024-11-29","cited_by_count":17,"area":null},{"id":"2503.04644","title":"IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval","created":"2025-03-06","cited_by_count":16,"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":"2506.03949","title":"TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering","created":"2025-06-04","cited_by_count":15,"area":null},{"id":"2211.16482","title":"Chaining Simultaneous Thoughts for Numerical Reasoning","created":"2022-11-29","cited_by_count":14,"area":null},{"id":"2402.12147","title":"Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models","created":"2024-02-19","cited_by_count":14,"area":null},{"id":"2505.20243","title":"It's High Time: A Survey of Temporal Question Answering","created":"2025-05-26","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":"2510.08886","title":"FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs","created":"2025-10-10","cited_by_count":14,"area":null},{"id":"2210.08249","title":"UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation","created":"2022-10-15","cited_by_count":13,"area":null},{"id":"2404.00699","title":"A Comprehensive Survey of Contamination Detection Methods in Large Language Models","created":"2024-03-31","cited_by_count":12,"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":"2309.10654","title":"CFGPT: Chinese Financial Assistant with Large Language Model","created":"2023-09-19","cited_by_count":11,"area":null},{"id":"2406.08398","title":"cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers","created":"2024-06-12","cited_by_count":11,"area":null},{"id":"2211.12668","title":"DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data","created":"2022-11-23","cited_by_count":10,"area":null},{"id":"2305.03458","title":"Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question","created":"2023-05-05","cited_by_count":10,"area":null},{"id":"2412.11757","title":"SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types","created":"2024-12-16","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":"2210.10350","title":"MuGER$^2$: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering","created":"2022-10-19","cited_by_count":9,"area":null},{"id":"2307.08260","title":"Extending the Frontier of ChatGPT: Code Generation and Debugging","created":"2023-07-17","cited_by_count":9,"area":null},{"id":"2310.06675","title":"SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQA","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2402.06733","title":"NICE: To Optimize In-Context Examples or Not?","created":"2024-02-09","cited_by_count":9,"area":null},{"id":"2404.11581","title":"E2ETune: End-to-End Knob Tuning via Fine-tuned Generative Language Model","created":"2024-04-17","cited_by_count":9,"area":null},{"id":"2408.13860","title":"Knowledge-Aware Reasoning over Multimodal Semi-structured Tables","created":"2024-08-25","cited_by_count":9,"area":null},{"id":"2505.21771","title":"MMTABREAL: Real-World Benchmark for Multimodal Table Understanding","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2507.17186","title":"FinGAIA: A Chinese Benchmark for AI Agents in Real-World Financial Domain","created":"2025-07-23","cited_by_count":9,"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":"2212.07249","title":"APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning","created":"2022-12-14","cited_by_count":8,"area":null},{"id":"2305.14901","title":"Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2501.04974","title":"SensorQA: A Question Answering Benchmark for Daily-Life Monitoring","created":"2025-01-09","cited_by_count":8,"area":null},{"id":"2505.16303","title":"INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2508.05201","title":"FAITH: A Framework for Assessing Intrinsic Tabular Hallucinations in Finance","created":"2025-08-07","cited_by_count":8,"area":null},{"id":"2508.21085","title":"Granite Embedding R2 Models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2510.15232","title":"FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain","created":"2025-10-17","cited_by_count":8,"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":"2212.13465","title":"A Survey on Table-and-Text HybridQA: Concepts, Methods, Challenges and Future Directions","created":"2022-12-27","cited_by_count":7,"area":null},{"id":"2311.14722","title":"Zero-Shot Question Answering over Financial Documents using Large Language Models","created":"2023-11-19","cited_by_count":7,"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":"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":"2503.12345","title":"General Table Question Answering via Answer-Formula Joint Generation","created":"2025-03-16","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":"2601.08689","title":"QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models","created":"2026-01-13","cited_by_count":7,"area":null},{"id":"2211.07455","title":"Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2212.10097","title":"Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2309.11049","title":"Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables","created":"2023-09-20","cited_by_count":6,"area":null}],"next_cursor":"100"}