KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues
First-ever benchmark for evaluating multi-turn long-form question answering in knowledge-intensive domains.
Sep 26, 2025
Interpreting Fedspeak with Confidence: A LLM-Based Uncertainty-Aware Framework
An LLM-based uncertainty-aware framework for interpreting Federal Reserve communications with enhanced reliability.
Aug 12, 2025
Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation
The first large-scale Chinese dataset for financial regulatory compliance with automated checking pipeline.
May 19, 2025