{"total":16,"rows":[{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243,"area":null},{"id":"2504.02901","title":"Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLM-Powered Assistance","created":"2025-04-03","cited_by_count":11,"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":"2412.10008","title":"Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language","created":"2024-12-13","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":"2512.13040","title":"Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection","created":"2025-12-15","cited_by_count":4,"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":"2601.13922","title":"Automatic Prompt Optimization for Dataset-Level Feature Discovery","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2501.11712","title":"YouLeQD: Decoding the Cognitive Complexity of Questions and Engagement in Online Educational Videos from Learners' Perspectives","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2505.14918","title":"Reliable Decision Support with LLMs: A Framework for Evaluating Consistency in Binary Text Classification Applications","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2507.00718","title":"AI Analyst: Framework and Comprehensive Evaluation of Large Language Models for Financial Time Series Report Generation","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2601.11920","title":"Enhancing LLM-Based Data Annotation with Error Decomposition","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2409.16710","title":"Beyond Turing Test: Can GPT-4 Sway Experts' Decisions?","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2508.08262","title":"Argument Quality Annotation and Gender Bias Detection in Financial Communication through Large Language Models","created":"2025-07-22","cited_by_count":0,"area":null},{"id":"2608.18158","title":"When Do LLMs Actually Help? Evaluating LLMs as Data Quality Annotators","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2610.14101","title":"Fin_Agent at FinEval 2026: Task-Aware Methods for Multilingual Financial NLP","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}