2025/02/10 by Hieu Trung Nguyen, Nguyen, Hieu Trung, Bao Nguyen +5 · 3 citations
Neuroscience · #EEG and Brain-Computer Interfaces #Neuroscience and Neural Engineering
paper · pdf · doi:10.48550/arxiv.2502.06115
Modern language models (LMs) have significantly advanced generative modeling in natural language processing (NLP). Despite their success, LMs often struggle with adaptation to new contexts in real-time applications. A promising approach to task adaptation is activation intervention, which steers the LMs' generation process by identifying and manipulating the activations. However, existing interventions are highly dependent on heuristic rules or require many prompt inputs to determine effective interventions. This paper proposes a layer-wise additive activation intervention framework that optimizes the intervention process, thus enhancing the sample efficiency. We benchmark our framework on various datasets, demonstrating improvements in the accuracy of pre-trained LMs and competing intervention baselines.