Related papers: Layer-Wise Evolution of Representations in Fine-Tu…

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

Artificial intelligence (AI) is anticipated to emerge as a pivotal enabler for the forthcoming sixth-generation (6G) wireless communication systems. However, current research efforts regarding large AI models for wireless communications…

Autoencoders are certainly among the most studied and used Deep Learning models: the idea behind them is to train a model in order to reconstruct the same input data. The peculiarity of these models is to compress the information through a…

Pretrained bidirectional Transformers, such as BERT, have achieved significant improvements in a wide variety of language understanding tasks, while it is not straightforward to directly apply them for natural language generation. In this…

Pretrained Language Models (PLMs) have become the de facto starting point for fine-tuning on downstream tasks. However, as model sizes continue to increase, traditional fine-tuning of all the parameters becomes challenging. To address this,…

Existing fine-tuning methods use a single learning rate over all layers. In this paper, first, we discuss that trends of layer-wise weight variations by fine-tuning using a single learning rate do not match the well-known notion that…

Low-Rank Adaptation (LoRA) has emerged as a widely adopted approach for adapting large language models, yet the internal representational changes induced by LoRA fine-tuning remain insufficiently understood. In this work, we investigate the…

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to costly training a large-scale model from scratch, how to…

Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various downstream tasks. However, most fine-tuning approaches update all the parameters of the…

Adjusting the latency, power, and accuracy of natural language understanding models is a desirable objective of an efficient architecture. This paper proposes an efficient Transformer architecture that adjusts the inference computational…

Fine-tuning adapts pretrained networks to new objectives. Whether the resulting depth profile of representational change reflects an intrinsic property of the model or the magnitude of gradient flow has not been tested directly. We measure…

Finetuning language models (LMs) is crucial for adapting the models to downstream data and tasks. However, full finetuning is usually costly. Existing work, such as parameter-efficient finetuning (PEFT), often focuses on \textit{how to…

Analyzing the similarity of internal representations has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the similarity between representations of high dimensions, such…

Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a…

Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract generally useful linguistic…

Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This way would not work as expected due to the intermediate…

Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-text inputs. Yet despite these gains, it remains unclear how…

Sparse autoencoders (SAEs) have emerged as a promising approach for learning interpretable features from neural network activations. However, the optimization landscape for SAE training can be challenging due to correlations in the input…

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which…

Sparse auto-encoders (SAEs) have become a prevalent tool for interpreting language models' inner workings. However, it is unknown how tightly SAE features correspond to computationally important directions in the model. This work…