Yu Xia

Yiran Shen, Yu Xia, Jonathan Chang et al.

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model across various domains spanning those with: verifiable rewards (mathematical accuracy), non-verifiable subjective preferences (human values), and complex interactive scenarios (multi-turn AI tutoring dialogues). Such multi-objective reinforcement learning setups are often plagued by the individual objectives being at odds with each other, resulting in inefficient training and little user control during inference. We propose a unified framework that: (i) standardizes {process reward model} (PRM) training across both verifiable and non-verifiable settings to better supervise models' chain-of-thought reasoning; (ii) performs {multi-objective alignment} by training the LLM with our $\textbf{M}$ulti-$\textbf{A}$ction-$\textbf{H}$ead $\textbf{DPO}$ (MAH-DPO) and a vectorized reward where the dimensions of the vector correspond to the various objectives instead of a single scalar; and (iii) demonstrates how such a system provides fine-grained inference-time user control. Experiments across math reasoning, value alignment, and multi-turn dialogue show that our framework improves performance across multiple objectives simultaneously, while minimizing cross-objective trade-offs and enabling flexible inference time user control. The code can be found at https://github.com/pearls-lab/multiobj-align.

Wenwen Zhang, Zhouzhuo Tang, Yingmei Feng et al.

During the early stages of respiratory virus outbreaks, such as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the efficient utilize of limited nasopharyngeal swabs for rapid and accurate screening is crucial for public health. In this study, we present a methodology that integrates attenuated total reflection-Fourier transform infrared spectroscopy (ATR-FTIR) with the adaptive iteratively reweighted penalized least squares (airPLS) preprocessing algorithm and a channel-wise attention-based partial least squares one-dimensional convolutional neural network (PLS-1D-CNN) model, enabling accurate screening of infected individuals within 10 minutes. Two cohorts of nasopharyngeal swab samples, comprising 126 and 112 samples from suspected SARS-CoV-2 Omicron variant cases, were collected at Beijing You'an Hospital for verification. Given that ATR-FTIR spectra are highly sensitive to variations in experimental conditions, which can affect their quality, we propose a biomolecular importance (BMI) evaluation method to assess signal quality across different conditions, validated by comparing BMI with PLS-GBM and PLS-RF results. For the ATR-FTIR signals in cohort 2, which exhibited a higher BMI, airPLS was utilized for signal preprocessing, followed by the application of the channel-wise attention-based PLS-1D-CNN model for screening. The experimental results demonstrate that our model outperforms recently reported methods in the field of respiratory virus spectrum detection, achieving a recognition screening accuracy of 96.48%, a sensitivity of 96.24%, a specificity of 97.14%, an F1-score of 96.12%, and an AUC of 0.99. It meets the World Health Organization (WHO) recommended criteria for an acceptable product: sensitivity of 95.00% or greater and specificity of 97.00% or greater for testing prior SARS-CoV-2 infection in moderate to high volume scenarios.