8 papers
Reasoning Scaffolding: Distilling the Flow of Thought from LLMs
Xiangyu Wen, Junhua Huang, Zeju Li +6
The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Mod…
Reinforcement Learning on Pre-Training Data
Siheng Li, Kejiao Li, Zenan Xu +33
The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for…
From Samples to Scenarios: A New Paradigm for Probabilistic Forecasting
Xilin Dai, Zhijian Xu, Wanxu Cai +1
Most state-of-the-art probabilistic time series forecasting models rely on sampling to represent future uncertainty. However, this paradigm suffers from inherent limitations, such…
Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy
Zeju Li, Jianyuan Zhong, Ziyang Zheng +5
Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting excel at complex reasoning but generate verbose thought processes with considerable redundancy, leading to incre…
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Xumeng Wen, Zihan Liu, Shun Zheng +9
Recent advancements in long chain-of-thought (CoT) reasoning, particularly through the Group Relative Policy Optimization algorithm used by DeepSeek-R1, have led to significant int…
Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier
Jianyuan Zhong, Zeju Li, Zhijian Xu +3
Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification,…