{"total":19,"rows":[{"id":"2410.21195","title":"Belief in the Machine: Investigating Epistemological Blind Spots of Language Models","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2506.08762","title":"EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2509.21155","title":"Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2603.02702","title":"FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing","created":"2026-03-03","cited_by_count":5,"area":null},{"id":"2412.19784","title":"Can AI Help with Your Personal Finances?","created":"2024-12-27","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":"2411.06852","title":"Evaluating Large Language Models on Financial Report Summarization: An Empirical Study","created":"2024-11-11","cited_by_count":3,"area":null},{"id":"2504.21625","title":"Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability","created":"2025-04-30","cited_by_count":3,"area":null},{"id":"2410.14059","title":"UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2507.22936","title":"Evaluating Large Language Models (LLMs) in Financial NLP: A Comparative Study on Financial Report Analysis","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2510.15691","title":"Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2606.26062","title":"When Certainty Is an Artifact: Keyword Lexicon Blindness and the (Mis)Measurement of Rhetorical Stance","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2505.19430","title":"Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2507.00347","title":"VTS-Guided AI Interaction Workflow for Business Insights","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2510.01638","title":"Towards Human-Centered RegTech: Unpacking Professionals' Strategies and Needs for Using LLMs Safely","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.10526","title":"Integrating Large Language Models and Reinforcement Learning for Sentiment-Driven Quantitative Trading","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2606.31461","title":"CSTrader: A Testbed for Language-Grounded Trading in a Community-Driven Virtual Asset Market","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.08634","title":"Can Open-Weight Models Compete on Financial Text Comprehension?","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2609.20232","title":"The Public Discourse Corpus (PDC): A Speaker-Attributed Dataset for Valence and Epistemic Modality with Target Speaker Participation","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":null}