Search Results for author:
Found 5 papers, 2 papers with code
Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
Our proposed framework can push the fine-tuned model to approach the bias lower bound during downstream fine-tuning, indicating that the ineffectiveness of debiasing can be alleviated by overcoming the forgetting issue through regularizing successfully debiased attention heads based on the PLMs' bias levels from stages of pretraining and debiasing.
On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept
When these instructions lack specific details about the issues in the response, this is referred to as leveraging the intrinsic self-correction capability.
Initialization Matters for Adversarial Transfer Learning
Based on this, we propose Robust Linear Initialization (RoLI) for adversarial finetuning, which initializes the linear head with the weights obtained by adversarial linear probing to maximally inherit the robustness from pretraining.
PAC-tuning:Fine-tuning Pretrained Language Models with PAC-driven Perturbed Gradient Descent
Fine-tuning pretrained language models (PLMs) for downstream tasks is a large-scale optimization problem, in which the choice of the training algorithm critically determines how well the trained model can generalize to unseen test data, especially in the context of few-shot learning.
Region Comparison Network for Interpretable Few-shot Image Classification
For that, in this work, we propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works as in a neural network as well as to find out specific regions that are related to each other in images coming from the query and support sets.
Ranked #33 on
Few-Shot Image Classification
on CIFAR-FS 5-way (5-shot)
