6 papers
Reinforcement Learning for LLM Post-Training: A Survey
Zhichao Wang, Kiran Ramnath, Bin Bi +9
Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding.…
UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function
Zhichao Wang, Bin Bi, Zixu Zhu +6
By pretraining on trillions of tokens, an LLM gains the capability of text generation. However, to enhance its utility and reduce potential harm, SFT and alignment are applied sequ…
UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types
Zhichao Wang, Bin Bi, Can Huang +7
RL alignment methods, including RLHF and DPO, are primarily based on pairwise preference data. Although scalar or score-based feedback has been collected in some settings, it is ra…
Markup Language Modeling for Web Document Understanding
Su Liu, Bin Bi, Jan Bakus +3
Web information extraction (WIE) is an important part of many e-commerce systems, supporting tasks like customer analysis and product recommendation. In this work, we look at the p…
Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models
Aliyah R. Hsu, James Zhu, Zhichao Wang +11
LLMs have demonstrated impressive proficiency in generating coherent and high-quality text, making them valuable across a range of text-generation tasks. However, rigorous evaluati…
Diversity Enhances an LLM's Performance in RAG and Long-context Task
Zhichao Wang, Bin Bi, Yanqi Luo +2
The rapid advancements in large language models (LLMs) have highlighted the challenge of context window limitations, primarily due to the quadratic time complexity of the self-atte…