A Tale of Tails: Model Collapse as a Change of Scaling Laws
Paper
•
2402.07043
•
Published
•
16
read
-
-
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT
Paper • 2509.19284 • Published • 22 -
OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System
Paper • 2509.18091 • Published • 32 -
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM
Paper • 2509.18058 • Published • 12 -
Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
Paper • 2508.21476 • Published • 2 -
Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
Paper • 2404.14461 • Published • 3 -
Universal Jailbreak Backdoors from Poisoned Human Feedback
Paper • 2311.14455 • Published • 2