Tianyi Wu

IGN : Implicit Generative Networks

2022

In this work, we build recent advances in distributional reinforcement learning to give a state-of-art distributional variant of the model based on the IQN. We achieve this by using the GAN model’s generator and discriminator …

Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning

2025 · arXiv (Cornell University)

Instruction fine-tuning (IFT) can increase the informativeness of large language models (LLMs), but may reduce their truthfulness. This trade-off arises because IFT steers LLMs to generate responses containing long-tail knowledge that was not well covered …