Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity Paper • 2601.06596 • Published 16 days ago • 12
WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research Paper • 2509.13312 • Published Sep 16, 2025 • 105