collaborators

5 papers

cs.AI2026

AI Engram: In Search of Memory Traces in Artificial Intelligence

Jea Kwon, Dong-Kyum Kim, Jiwon Kim +3

Memory formation is fundamental to intelligence, yet whether deep neural networks preserve identifiable memory traces analogous to biological memory units remains an open question.…

cs.CL2026

Moir: Let the Model Direct Its Own Story for Robust Cross-Domain Knowledge Editing

Jea Kwon, Jiwon Kim, Dong-kyum Kim +1

While language models remain frozen at their training state, the world evolves continuously. Knowledge editing has emerged as a key alternative to full retraining, but its deployme…

cs.CL2026

How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models

Minsung Kim, Dong-Kyum Kim, Jea Kwon +3

Large language models leverage both parametric knowledge acquired during pretraining and in-context knowledge provided at inference time. Crucially, when these sources conflict, mo…

cs.LG2026

Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning

Nakyeong Yang, Dong-Kyum Kim, Jea Kwon +3

Large language models trained on web-scale data can memorize private or sensitive knowledge, raising significant privacy risks. Although some unlearning methods mitigate these risk…

cs.AI2026

Bilinear representation mitigates reversal curse and enables consistent model editing

Dong-Kyum Kim, Minsung Kim, Jea Kwon +2

The reversal curse--a language model's inability to infer an unseen fact "B is A" from a learned fact "A is B"--is widely considered a fundamental limitation. We show that this is…