{"total":117,"rows":[{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"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":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"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":"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":"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":"2402.02315","title":"A Survey of Large Language Models in Finance (FinLLMs)","created":"2024-02-04","cited_by_count":79,"area":null},{"id":"2305.07972","title":"Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis","created":"2023-05-13","cited_by_count":75,"area":null},{"id":"2310.04793","title":"FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets","created":"2023-10-07","cited_by_count":69,"area":null},{"id":"2412.18174","title":"INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent","created":"2024-12-24","cited_by_count":64,"area":"agents"},{"id":"2310.15051","title":"TeleQnA: A Benchmark Dataset to Assess Large Language Models Telecommunications Knowledge","created":"2023-10-23","cited_by_count":63,"area":null},{"id":"2302.09432","title":"BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark","created":"2023-02-18","cited_by_count":60,"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":"2306.12659","title":"Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models","created":"2023-06-22","cited_by_count":58,"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":"2502.10708","title":"Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey","created":"2025-02-15","cited_by_count":51,"area":null},{"id":"2401.05799","title":"Designing Heterogeneous LLM Agents for Financial Sentiment Analysis","created":"2024-01-11","cited_by_count":48,"area":"agents"},{"id":"2402.05131","title":"Financial Report Chunking for Effective Retrieval Augmented Generation","created":"2024-02-05","cited_by_count":46,"area":"rag"},{"id":"2403.16008","title":"CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering","created":"2024-03-24","cited_by_count":45,"area":null},{"id":"2510.02209","title":"StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?","created":"2025-10-02","cited_by_count":44,"area":"agents"},{"id":"2312.17482","title":"MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining","created":"2023-12-29","cited_by_count":34,"area":null},{"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":"2402.09552","title":"STEER: Assessing the Economic Rationality of Large Language Models","created":"2024-02-14","cited_by_count":27,"area":"lr"},{"id":"2406.19966","title":"Simulating Financial Market via Large Language Model based Agents","created":"2024-06-28","cited_by_count":25,"area":"agents"},{"id":"2310.00566","title":"Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Models","created":"2023-10-01","cited_by_count":24,"area":null},{"id":"2407.06245","title":"ORAN-Bench-13K: An Open Source Benchmark for Assessing LLMs in Open Radio Access Networks","created":"2024-07-08","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":"2502.11433","title":"FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2405.07938","title":"EconLogicQA: A Question-Answering Benchmark for Evaluating Large Language Models in Economic Sequential Reasoning","created":"2024-05-13","cited_by_count":22,"area":"lr"},{"id":"2505.19457","title":"BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs","created":"2025-05-26","cited_by_count":22,"area":null},{"id":"2305.01505","title":"Beyond Classification: Financial Reasoning in State-of-the-Art Language Models","created":"2023-04-30","cited_by_count":19,"area":"lr"},{"id":"2305.18322","title":"REFinD: Relation Extraction Financial Dataset","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17,"area":null},{"id":"2306.09237","title":"One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support","created":"2023-06-15","cited_by_count":16,"area":"lr"},{"id":"2305.16633","title":"Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks","created":"2023-05-26","cited_by_count":14,"area":null},{"id":"2511.03628","title":"LiveTradeBench: Seeking Real-World Alpha with Large Language Models","created":"2025-11-05","cited_by_count":13,"area":"lr"},{"id":"2407.02301","title":"CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models","created":"2024-07-02","cited_by_count":12,"area":null},{"id":"2411.00782","title":"TradExpert: Revolutionizing Trading with Mixture of Expert LLMs","created":"2024-10-16","cited_by_count":12,"area":"moe"},{"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":"2309.10654","title":"CFGPT: Chinese Financial Assistant with Large Language Model","created":"2023-09-19","cited_by_count":11,"area":null},{"id":"2310.12664","title":"Is ChatGPT a Financial Expert? Evaluating Language Models on Financial Natural Language Processing","created":"2023-10-19","cited_by_count":11,"area":null},{"id":"2306.02368","title":"Revisiting Data-Free Knowledge Distillation with Poisoned Teachers","created":"2023-06-04","cited_by_count":9,"area":"safety"},{"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":"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":"2412.15270","title":"Baichuan4-Finance Technical Report","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2307.10188","title":"Several categories of Large Language Models (LLMs): A Short Survey","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2311.01786","title":"TCM-GPT: Efficient Pre-training of Large Language Models for Domain Adaptation in Traditional Chinese Medicine","created":"2023-11-03","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":"2408.12263","title":"Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates","created":"2024-08-22","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":"2310.12620","title":"Predict the Future from the Past? On the Temporal Data Distribution Shift in Financial Sentiment Classifications","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2407.10784","title":"AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2310.07637","title":"OpsEval: A Comprehensive IT Operations Benchmark Suite for Large Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2311.04666","title":"Pre-training LLMs using human-like development data corpus","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2311.05286","title":"Causal Inference from Text: Unveiling Interactions between Variables","created":"2023-11-09","cited_by_count":5,"area":null},{"id":"2506.20274","title":"Enterprise Large Language Model Evaluation Benchmark","created":"2025-06-25","cited_by_count":5,"area":null},{"id":"2402.11728","title":"Numerical Claim Detection in Finance: A New Financial Dataset, Weak-Supervision Model, and Market Analysis","created":"2024-02-18","cited_by_count":4,"area":null},{"id":"2408.03762","title":"'Finance Wizard' at the FinLLM Challenge Task: Financial Text Summarization","created":"2024-08-07","cited_by_count":4,"area":null},{"id":"2411.06272","title":"Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models","created":"2024-11-09","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":"2507.18577","title":"Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challenges","created":"2025-07-07","cited_by_count":4,"area":null},{"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":"2603.07223","title":"Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2307.14852","title":"ArcGPT: A Large Language Model Tailored for Real-world Archival Applications","created":"2023-07-27","cited_by_count":3,"area":null},{"id":"2310.13312","title":"Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2406.15508","title":"What Teaches Robots to Walk, Teaches Them to Trade too -- Regime Adaptive Execution using Informed Data and LLMs","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2407.00365","title":"Financial Knowledge Large Language Model","created":"2024-06-29","cited_by_count":3,"area":null},{"id":"2410.07118","title":"Exploring the Readiness of Prominent Small Language Models for the Democratization of Financial Literacy","created":"2024-10-09","cited_by_count":3,"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":"2506.12958","title":"Domain Specific Benchmarks for Evaluating Multimodal Large Language Models","created":"2025-06-15","cited_by_count":3,"area":"mllm"},{"id":"2605.00706","title":"FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios","created":"2026-05-01","cited_by_count":3,"area":"safety"},{"id":"2605.27887","title":"PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2307.00132","title":"iMETRE: Incorporating Markers of Entity Types for Relation Extraction","created":"2023-06-30","cited_by_count":2,"area":null},{"id":"2403.12212","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2404.09260","title":"JaFIn: Japanese Financial Instruction Dataset","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2407.14727","title":"Economy Watchers Survey Provides Datasets and Tasks for Japanese Financial Domain","created":"2024-07-20","cited_by_count":2,"area":null},{"id":"2409.16452","title":"FMDLlama: Financial Misinformation Detection based on Large Language Models","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2503.20990","title":"FinAudio: A Benchmark for Audio Large Language Models in Financial Applications","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2504.11626","title":"Improving Instruct Models for Free: A Study on Partial Adaptation","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2506.02510","title":"M$^3$FinMeeting: A Multilingual, Multi-Sector, and Multi-Task Financial Meeting Understanding Evaluation Dataset","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.13066","title":"FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design","created":"2025-06-16","cited_by_count":2,"area":"lr"},{"id":"2508.07353","title":"Benchmarking for Domain-Specific LLMs: A Case Study on Academia and Beyond","created":"2025-08-10","cited_by_count":2,"area":null},{"id":"2509.04455","title":"INSEva: A Comprehensive Chinese Benchmark for Large Language Models in Insurance","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2602.10886","title":"The CLEF-2026 FinMMEval Lab: Multilingual and Multimodal Evaluation of Financial AI Systems","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2608.12342","title":"Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2405.09747","title":"NIFTY Financial News Headlines Dataset","created":"2024-05-16","cited_by_count":1,"area":"alignment"},{"id":"2407.21276","title":"Knowledge Pyramid Construction for Multi-Level Retrieval-Augmented Generation","created":"2024-07-31","cited_by_count":1,"area":"rag"},{"id":"2412.19361","title":"Dynamic Skill Adaptation for Large Language Models","created":"2024-12-26","cited_by_count":1,"area":null},{"id":"2502.15411","title":"HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2507.09601","title":"NMIXX: Domain-Adapted Neural Embeddings for Cross-Lingual eXploration of Finance","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2511.04705","title":"POLIS-Bench: Towards Multi-Dimensional Evaluation of LLMs for Bilingual Policy Tasks in Governmental Scenarios","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2601.02573","title":"LendNova: Towards Automated Credit Risk Assessment with Language Models","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2606.08051","title":"How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2608.04077","title":"FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.19558","title":"Reliable Financial Named Entity Recognition Under Domain Shift: Confidence Estimation and Selective Prediction","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2403.09702","title":"Generator-Guided Crowd Reaction Assessment","created":"2024-03-08","cited_by_count":0,"area":null}],"next_cursor":"100"}