Published in IEEE Open Journal of Signal Processing, 2023
We study contextual multi-armed bandit problem where the features are costly and the agent has to simultaneously learn the reward distributions and the feature importances. The environment undergoes distribution shifts making the problem more challenging.
Download here
Published in IEEE Open Journal of Signal Processing, 2023
Utilizing random projections to apply an MAB-algorithm to a recommender system scenario, where the data is high-dimensional and user preferences change over time.
Download here
Published in NeurIPS Workshop XAIA, 2023
Interviewing ML practitioners to explore the human factor of training data attribution explanations.
Recommended citation: Elisa Nguyen, Evgenii Kortukov, Jean Song, and Seong Joon Oh. Exploring practitioner perspectives on training data attribution explanations. In XAI in Action: Past, Present, and Future Applications, 2023. https://openreview.net/forum?id=x9H6lNez5b
Published in COLM, 2024
Studying context-memory knowledge conflicts as they appear in practice: how does factual knowledge influence LLM reading behaviors?
Download here
Published in ArXiv, 2024
Making XAI more useful by first asking the users about their needs, with a focus on Training Data Attribution.
Download here
Published in ICLR 2025 Workshop Building Trust in LLMs, 2025
We introduce an architectural change to LLMs that separates instructions from data, to improve their security.
Download here
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.