2 papers
cs.LG2025
Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach
Iing Muttakhiroh, Thomas Fevens
Despite the significant advancements in Large Language Models (LLMs), catastrophic forgetting remains a substantial challenge, where models lose previously acquired knowledge upon…
cs.CL2025
Tackling Distribution Shift in LLM via KILO: Knowledge-Instructed Learning for Continual Adaptation
Iing Muttakhiroh, Thomas Fevens
Large Language Models (LLMs) often suffer from performance degradation when faced with domain shifts, primarily due to catastrophic forgetting. In this work, we propose KILO (Knowl…