4 papers
Adaptive Self-Consistency: From Black-Box Sampling to Distribution-Valued Feedback
Jingkai Huang, Yunfan Zhang, Will Ma +2
Self-consistency samples many reasoning trajectories and aggregates their final answers, treating the LLM as a black box that returns one answer per trajectory. Yet the final answe…
Which Pairs to Compare for LLM Post-Training?
Jiangze Han, Vineet Goyal, Will Ma
Preference-based post-training has become a central paradigm for aligning language models. A common data-collection strategy is to generate a small set of completions for each prom…
Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
Jingkai Huang, Will Ma, Zhengyuan Zhou
A simple strategy for improving LLM accuracy, especially in math and reasoning problems, is to sample multiple responses and submit the answer most consistently reached. In this pa…
SynthIPD: training-free synthetic individual patient data generation
Zixuan Zhao, Zexin Ren, Guannan Zhai +4
Individual patient data (IPD) are essential for statistical inference in clinical research. However, privacy concerns, high data-sharing costs, and restrictive access often make IP…