6 papers
Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models
Ruiqi Zhang, Changyi Xiao, Yixin Cao
With the rapid advancement of large reasoning models, long Chain-of-Thought (CoT) prompting has demonstrated strong performance on complex tasks. However, this often comes with a s…
SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learning
Ruiqi Zhang, Daman Arora, Song Mei +1
Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive d…
Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes
Ruiqi Zhang, Jingfeng Wu, Licong Lin +1
We study (GD) for logistic regression on linearly separable data with stepsizes that adapt to the current risk, scaled by a constant hyperparameter .…
How Do LLMs Perform Two-Hop Reasoning in Context?
Tianyu Guo, Hanlin Zhu, Ruiqi Zhang +4
``Socrates is human. All humans are mortal. Therefore, Socrates is mortal.'' This form of argument illustrates a typical pattern of two-hop reasoning. Formally, two-hop reasoning r…
Fast Best-of-N Decoding via Speculative Rejection
Hanshi Sun, Momin Haider, Ruiqi Zhang +6
The safe and effective deployment of Large Language Models (LLMs) involves a critical step called alignment, which ensures that the model's responses are in accordance with human p…
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
Chongyu Fan, Jiancheng Liu, Licong Lin +4
This work studies the problem of large language model (LLM) unlearning, aiming to remove unwanted data influences (e.g., copyrighted or harmful content) while preserving model util…