We have 4 of 28 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Domain-specific continual adaptation of LLMs risks catastrophic forgetting, creating a fundamental tension between acquiring new capabilities and preserving those learned during pretraining. PEFT mitigates this problem by restricting the number of trainable parameters, but existing methods lack a principled unit for de...
Experiments across three language models and two multimodal models show that PIECE maintains general capabilities and achieves state-of-the-art continual learning performance across diverse downstream tasks, highlighting a practical path to scalable, domain-adaptive foundation models without catastrophic forgetting.
GRADE (GRAdient Dynamics for knowlEdge gap detection), which quantifies the knowledge gap via the cross-layer rank ratio of the gradient to that of the corresponding hidden state subspace, motivated by the property of gradients as estimators of the required knowledge updates for a given target.
This work proposes AURORA, a novel hallucination detection framework that shifts the focus from static representations to the weight-gradient dynamics of LLMs, and achieves strong hallucination detection performance across four model families and four benchmark datasets.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
