Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2508.09510 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912535903469568 |
|---|---|
| author | Muttakhiroh, Iing Fevens, Thomas |
| author_facet | Muttakhiroh, Iing Fevens, Thomas |
| contents | Despite the significant advancements in Large Language Models (LLMs), catastrophic forgetting remains a substantial challenge, where models lose previously acquired knowledge upon learning new information. Continual learning (CL) strategies have emerged as a potential solution to this problem, with replay-based techniques demonstrating superior performance in preserving learned knowledge. In this context, we introduce Gauss-Tin, a novel approach that integrates the replay strategy with a Gaussian mixture model to enhance the quality of sample selection during training, supplemented by instructional guidance to facilitate the generation of past learning. This method aims to improve LLMs' retention capabilities by strategically reinforcing important past learnings while accommodating new information. Our experimental results indicate a promising 6\% improvement in retention metrics over traditional methods, suggesting that Gauss-Tin is an effective strategy for mitigating catastrophic forgetting in LLMs. This study underscores the potential of hybrid models in enhancing the robustness and adaptability of LLMs in dynamic learning environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09510 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach Muttakhiroh, Iing Fevens, Thomas Machine Learning Despite the significant advancements in Large Language Models (LLMs), catastrophic forgetting remains a substantial challenge, where models lose previously acquired knowledge upon learning new information. Continual learning (CL) strategies have emerged as a potential solution to this problem, with replay-based techniques demonstrating superior performance in preserving learned knowledge. In this context, we introduce Gauss-Tin, a novel approach that integrates the replay strategy with a Gaussian mixture model to enhance the quality of sample selection during training, supplemented by instructional guidance to facilitate the generation of past learning. This method aims to improve LLMs' retention capabilities by strategically reinforcing important past learnings while accommodating new information. Our experimental results indicate a promising 6\% improvement in retention metrics over traditional methods, suggesting that Gauss-Tin is an effective strategy for mitigating catastrophic forgetting in LLMs. This study underscores the potential of hybrid models in enhancing the robustness and adaptability of LLMs in dynamic learning environments. |
| title | Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.09510 |