6 papers
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
ByteDance Seed, :, Jiaze Chen +267
We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 8…
Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback
Wei Shen, Guanlin Liu, Zheng Wu +5
Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning large language models with human preferences. While recent research has focused on algorithmic improvement…
Knowledge Distillation with Training Wheels
Guanlin Liu, Anand Ramachandran, Tanmay Gangwani +2
Knowledge distillation is used, in generative language modeling, to train a smaller student model using the help of a larger teacher model, resulting in improved capabilities for t…
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
Weizhe Chen, Zhicheng Zhang, Guanlin Liu +6
Since the release of ChatGPT, large language models (LLMs) have demonstrated remarkable capabilities across various domains. A key challenge in developing these general capabilitie…
Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization
Kaixuan Ji, Guanlin Liu, Ning Dai +6
Reinforcement Learning (RL) plays a crucial role in aligning large language models (LLMs) with human preferences and improving their ability to perform complex tasks. However, curr…
Process Supervision-Guided Policy Optimization for Code Generation
Ning Dai, Zheng Wu, Renjie Zheng +7
Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evalu…