Towards Effective Counter-Responses: Aligning Human Preferences with Strategies to Combat Online Trolling Paper • 2410.04164 • Published Oct 5, 2024
Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation Paper • 2506.19352 • Published Jun 24, 2025
MentalBench: A Benchmark for Evaluating Psychiatric Diagnostic Capability of Large Language Models Paper • 2602.12871 • Published Feb 13 • 5