3 papers
cs.CL2025
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
Jiahao Qiu, Yifu Lu, Yifan Zeng +9
Inference-time alignment enhances the performance of large language models without requiring additional training or fine-tuning but presents challenges due to balancing computation…
cs.LG2025
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
Hui Yuan, Yifan Zeng, Yue Wu +3
Reinforcement Learning from Human Feedback (RLHF) has become the predominant approach for language model (LM) alignment. At its core, RLHF uses a margin-based loss for preference o…
cs.LG2025
Machine Learning for Synthetic Data Generation: A Review
Yingzhou Lu, Lulu Chen, Yuanyuan Zhang +6
Machine learning heavily relies on data, but real-world applications often encounter various data-related issues. These include data of poor quality, insufficient data points leadi…