{"total":30,"rows":[{"id":"2503.01875","title":"Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement","created":"2025-02-26","cited_by_count":82,"area":null},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54,"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":"2501.17144","title":"FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data","created":"2025-01-28","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":"2510.15232","title":"FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain","created":"2025-10-17","cited_by_count":8,"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":"2503.22693","title":"Bridging Language Models and Financial Analysis","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2603.04403","title":"FinRetrieval: A Benchmark for Financial Data Retrieval by AI Agents","created":"2026-01-02","cited_by_count":4,"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":"2504.17366","title":"LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams","created":"2025-04-24","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":"2509.21732","title":"How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2509.21856","title":"KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2602.18481","title":"AlphaForgeBench: Benchmarking End-to-End Trading Strategy Design with Large Language Models","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2503.15985","title":"Exploring the Reliability of Self-explanation and its Relationship with Classification in Language Model-driven Financial Analysis","created":"2025-03-20","cited_by_count":1,"area":null},{"id":"2509.24342","title":"Fin-Ally: Pioneering the Development of an Advanced, Commonsense-Embedded Conversational AI for Money Matters","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2601.15511","title":"AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2604.05387","title":"Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.08614","title":"DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.08932","title":"From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2608.07400","title":"FinRank: An Evidence-Grounded Benchmark for Financial Question Answering and Retrieval over SEC Filings","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2506.07315","title":"Towards Competent AI for Fundamental Analysis in Finance: A Benchmark Dataset and Evaluation","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2508.02222","title":"FinCPRG: A Bidirectional Generation Pipeline for Hierarchical Queries and Rich Relevance in Financial Chinese Passage Retrieval","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.08001","title":"Interpreting Fedspeak with Confidence: A LLM-Based Uncertainty-Aware Framework Guided by Monetary Policy Transmission Paths","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2511.03635","title":"Towards Transparent Stance Detection: A Zero-Shot Approach Using Implicit and Explicit Interpretability","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2511.05000","title":"Query Generation Pipeline with Enhanced Answerability Assessment for Financial Information Retrieval","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2609.00999","title":"Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.06117","title":"STQA: A Benchmark for Stock-Focused Tabular Question Answering over Historical and Forecasted Data","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.33505","title":"When Evidence Changes the Subject: Subject-Typed Claim Licensing for Learned Routing","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}