Search Results for author:
Found 4 papers, 2 papers with code
Noise Contrastive Alignment of Language Models with Explicit Rewards
Existing alignment methods, such as Direct Preference Optimization (DPO), are mainly tailored for pairwise preference data where rewards are implicitly defined rather than explicitly given.
Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis
Specifically, we leverage the latent representation obtained from text input as our prior, and build a fully tractable Schrodinger bridge between it and the ground-truth mel-spectrogram, leading to a data-to-data process.
Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting
Despite the significant progress made in practical applications of aligned language models (LMs), they tend to be overconfident in output answers compared to the corresponding pre-trained LMs.
Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models
In light of these observations, we evaluate the calibration of several methods that preserve pre-trained features and show that preserving pre-trained features can improve the calibration of fine-tuned language models.
