21 papers · 1 filter
One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL
Simon Yu, Nicholas Tomlin, Marwa Abdulhai +7
Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach systematically f…
CreativityPrism: A Cross-Domain Evaluation Framework for Large Language Model Creativity
Zhaoyi Joey Hou, Bowei Alvin Zhang, Yining Lu +9
Creativity is often seen as a hallmark of human intelligence. While large language models(LLMs) are increasingly perceived as generating creative text, there is still no cross-doma…
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
Byung-Kwan Lee, Ximing Lu, Shizhe Diao +8
Knowledge distillation transfers a teacher's competence to a small student but is brittle in the small-student regime: forcing the student to imitate logits from a much larger teac…
ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge
Zhilin Wang, Jaehun Jung, Ximing Lu +7
Evaluating progress in large language models (LLMs) is often constrained by the challenge of verifying responses, limiting assessments to tasks like mathematics, programming, and s…
The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
Skyler Hallinan, Jaehun Jung, Melanie Sclar +7
Membership inference attacks serves as useful tool for fair use of language models, such as detecting potential copyright infringement and auditing data leakage. However, many curr…
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Shih-Yang Liu, Xin Dong, Ximing Lu +10
As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety…