5 papers · 1 filter
Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport
Minseok Choi, Daniel Rim, Dohyun Lee +1
Instruction-following large language models (LLMs), such as ChatGPT, have become widely popular among everyday users. However, these models inadvertently disclose private, sensitiv…
Exploring In-context Example Generation for Machine Translation
Dohyun Lee, Seungil Chad Lee, Chanwoo Yang +2
Large language models (LLMs) have demonstrated strong performance across various tasks, leveraging their exceptional in-context learning ability with only a few examples. According…
Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning
Minseok Choi, ChaeHun Park, Dohyun Lee +1
Large language models (LLMs) serve as giant information stores, often including personal or copyrighted data, and retraining them from scratch is not a viable option. This has led…
PairEval: Open-domain Dialogue Evaluation with Pairwise Comparison
ChaeHun Park, Minseok Choi, Dohyun Lee +1
Building a reliable and automated evaluation metric is a necessary but challenging problem for open-domain dialogue systems. Recent studies proposed evaluation metrics that assess…
Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models
Dohyun Lee, Daniel Rim, Minseok Choi +1
Although language models (LMs) demonstrate exceptional capabilities on various tasks, they are potentially vulnerable to extraction attacks, which represent a significant privacy r…