{"total":230,"rows":[{"id":"2311.11944","title":"FinanceBench: A New Benchmark for Financial Question Answering","created":"2023-11-20","cited_by_count":270,"area":null},{"id":"2305.12524","title":"TheoremQA: A Theorem-driven Question Answering dataset","created":"2023-05-21","cited_by_count":192,"area":null},{"id":"2402.17944","title":"Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey","created":"2024-02-27","cited_by_count":159,"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":"2305.13626","title":"Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration","created":"2023-05-23","cited_by_count":116,"area":null},{"id":"2406.14991","title":"SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation","created":"2024-06-21","cited_by_count":111,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","cited_by_count":82,"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":"2403.19318","title":"TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios","created":"2024-03-28","cited_by_count":77,"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":"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":"2106.12944","title":"AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry","created":"2021-06-24","cited_by_count":44,"area":null},{"id":"2406.08100","title":"Multimodal Table Understanding","created":"2024-06-12","cited_by_count":44,"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":"2207.05270","title":"A Survey on Table Question Answering: Recent Advances","created":"2022-07-12","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":"2305.12820","title":"MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering","created":"2023-05-22","cited_by_count":32,"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":"2311.08002","title":"TempTabQA: Temporal Question Answering for Semi-Structured Tables","created":"2023-11-14","cited_by_count":27,"area":null},{"id":"2204.11677","title":"Conversational Question Answering on Heterogeneous Sources","created":"2022-04-25","cited_by_count":26,"area":null},{"id":"2305.14010","title":"IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2402.12869","title":"Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data","created":"2024-02-20","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":"2506.05725","title":"Large Language Models are Good Relational Learners","created":"2025-06-06","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":"2306.16762","title":"Unified Language Representation for Question Answering over Text, Tables, and Images","created":"2023-06-29","cited_by_count":22,"area":null},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"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":"2109.07323","title":"FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining","created":"2021-09-15","cited_by_count":19,"area":null},{"id":"2408.10548","title":"Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution","created":"2024-08-20","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":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2309.04790","title":"MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images","created":"2023-09-09","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":"2105.11776","title":"Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering","created":"2021-05-25","cited_by_count":17,"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":"2210.05197","title":"Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA","created":"2022-10-11","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":"2404.18585","title":"FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering","created":"2024-04-29","cited_by_count":16,"area":null},{"id":"2406.14971","title":"Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation","created":"2024-06-21","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":"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":"2310.14687","title":"API-Assisted Code Generation for Question Answering on Varied Table Structures","created":"2023-10-23","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":"2409.18511","title":"Do We Need Domain-Specific Embedding Models? An Empirical Investigation","created":"2024-09-27","cited_by_count":12,"area":null},{"id":"2506.13405","title":"RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis","created":"2025-06-16","cited_by_count":12,"area":null},{"id":"2204.03357","title":"Parameter-Efficient Abstractive Question Answering over Tables or Text","created":"2022-04-07","cited_by_count":11,"area":null},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","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":"2602.19549","title":"Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework","created":"2026-02-23","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":"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":"2406.12719","title":"Exploring the Robustness of Language Models for Tabular Question Answering via Attention Analysis","created":"2024-06-18","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":"2409.16682","title":"SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA","created":"2024-09-25","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":"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":"2212.02691","title":"LUNA: Language Understanding with Number Augmentations on Transformers via Number Plugins and Pre-training","created":"2022-12-06","cited_by_count":8,"area":null},{"id":"2402.10812","title":"Exploring Hybrid Question Answering via Program-based Prompting","created":"2024-02-16","cited_by_count":8,"area":null},{"id":"2402.10979","title":"SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs","created":"2024-02-15","cited_by_count":8,"area":null},{"id":"2402.14853","title":"NL2Formula: Generating Spreadsheet Formulas from Natural Language Queries","created":"2024-02-20","cited_by_count":8,"area":null},{"id":"2410.20651","title":"SubjECTive-QA: Measuring Subjectivity in Earnings Call Transcripts' QA Through Six-Dimensional Feature Analysis","created":"2024-10-28","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":"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":"2605.20270","title":"Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs","created":"2026-05-18","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":"2410.03576","title":"Table Question Answering for Low-resourced Indic Languages","created":"2024-10-04","cited_by_count":7,"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":"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":"2504.04596","title":"SECQUE: A Benchmark for Evaluating Real-World Financial Analysis Capabilities","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2506.04427","title":"Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance","created":"2025-06-04","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},{"id":"2403.02528","title":"DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation","created":"2024-03-04","cited_by_count":6,"area":null},{"id":"2405.07765","title":"TANQ: An open domain dataset of table answered questions","created":"2024-05-13","cited_by_count":6,"area":null},{"id":"2408.11490","title":"DocTabQA: Answering Questions from Long Documents Using Tables","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2507.20930","title":"FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models","created":"2025-07-28","cited_by_count":6,"area":null},{"id":"2207.05875","title":"A Novel DeBERTa-based Model for Financial Question Answering Task","created":"2022-07-12","cited_by_count":5,"area":null},{"id":"2305.01938","title":"Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2305.14007","title":"When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2405.08099","title":"KET-QA: A Dataset for Knowledge Enhanced Table Question Answering","created":"2024-05-13","cited_by_count":5,"area":null},{"id":"2406.00975","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","created":"2024-06-03","cited_by_count":5,"area":null}],"next_cursor":"100"}