Search Results for author:
Found 4 papers, 2 papers with code
PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack
To reduce the potential side effects of using defense modules, we further propose a novel forgetting restricted adversarial training, which filters out bad adversarial examples that impair the performance of original ones.
Mitigating Reward Hacking via Information-Theoretic Reward Modeling
Inspired by this finding, we propose the Integrated Cluster Deviation Score (ICDS), which quantifies deviations in the latent space, as an indicator of reward overoptimization to facilitate the development of online mitigation strategies.
Orthogonal Subspace Learning for Language Model Continual Learning
In this paper, we propose orthogonal low-rank adaptation (O-LoRA), a simple and efficient approach for continual learning in language models, effectively mitigating catastrophic forgetting while learning new tasks.
Robust Lottery Tickets for Pre-trained Language Models
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.
