Papers by Arda Akdemir
Research on Task Discovery for Transfer Learning in Deep Neural Networks (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing deep neural network based machine learning models suffer from overfitting and are sensitive to noise and examples that are not available in training data. |
| Approach: | They propose to use a novel multi-task learner to implement deep neural network based transfer learning models that can be used to improve generalization. |
| Outcome: | The proposed model performs better on two NLP tasks and is more efficient on other areas of machine learning, including Bioinformatics and Computer Vision. |
Developing Language Resources and NLP Tools for the North Korean Language (2022.lrec-1)
Copied to clipboard
| Challenge: | There are no linguistic sources for the North Korean language, resulting in a lack of a Korean language model. |
| Approach: | They present a large-scale dataset for the North Korean language and annotate a subset of this dataset for a sentiment analysis task. |
| Outcome: | The proposed model performs better than other models for masked language modeling and sentiment analysis tasks. |
RAPIDS: Resume Attack Prompt Injection Detection at Scale (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing generic prompt injection detectors lack domain specificity needed for nuanced resume attacks. |
| Approach: | They propose a scalable detection framework that uses a synthetically generated dataset to address data scarcity in this domain. |
| Outcome: | The proposed framework outperforms the best off-the-shelf detector by over 50% in relative F1 and approaches frontier LLM accuracy. |