STABLE: Gated Continual Learning for Large Language Models
Large language models (LLMs) increasingly require mechanisms for continual adaptation without full retraining. However, sequential updates can lead to catastrophic forgetting, where new edits degrade previously acquired knowledge. This work presents STABLE, a gated continual self editing framework that constrains forgetting during sequential updates using parameter efficient fine tuning via Low Rank Adaptation (LoRA; see arXiv:2106.09685). Each candidate edit is evaluated against a stability budget using one of three metrics: (i) Exact Match (EM) drop, capturing factual accuracy loss; (ii) bits increase, reflecting reduced model confidence; and (iii) KL divergence, quantifying distributional drift between the base and adapted models. If a threshold is exceeded, the LoRA update is rescaled through a clipping procedure or rejected. Experiments on the Qwen-2.5-7B model show that gating effectively mitigates forgetting while preserving adaptability. EM based gating achieved the highest cumulative performance in short continual learning sequences. Our results show that different gating strategies can achieve comparable distribution shift (measured by KL divergence) while producing different accuracy outcomes, highlighting the importance of gating design in continual adaptation. This approach offers a principled method for continual model editing, enabling LLMs to integrate new knowledge while maintaining reliability. Code: https://github.com/Bhoy1/STABLE
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningSimilar Papers 제목 키워드 기반
Minion Gated Recurrent Unit for Continual Learning
The increasing demand for continual learning in sequential data processing has led to progressively complex training methodologies and larger recurrent network architectures. Consequently, this has widened the knowledge …
Continual Learningimage-classificationImage ClassificationSequential Image ClassificationLarge Language Model Empowered Recommendation Meets All-domain Continual Pre-Training
Recent research efforts have investigated how to integrate Large Language Models (LLMs) into recommendation, capitalizing on their semantic comprehension and open-world knowledge for user behavior understanding. These ap…
AllLanguage ModelingLanguage ModellingLarge Language Model+1Continual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMs
We study dense-to-sparse continual training as a way to construct channel-sparse large language models from dense checkpoints. Starting from a Qwen2.5-8B dense backbone, we continue training at 32K context and introduce …
Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints
Locally deployed Small Language Models (SLMs) must continually support diverse tasks under strict memory and computation constraints, making selective reliance on cloud Large Language Models (LLMs) unavoidable. Regulatin…
Reinforcement LearningMathematical ReasoningContinual LearningCode GenerationCP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning
Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scalin…
Continual LearningVisual Reasoning